Total: 415
2023 (4)
-
A. Mehler, M. Bagci, A. Henlein, G. Abrami, C. Spiekermann, P. Schrottenbacher, M. Konca, A. Lücking, J. Engel, M. Quintino, J. Schreiber, K. Saukel, and O. Zlatkin-Troitschanskaia, “A Multimodal Data Model for Simulation-based Learning with Va.Si.Li-Lab,” in Proceedings of HCI International 2023, 2023. accpeted
[BibTeX]@inproceedings{Mehler:et:al:2023:a, author = {Alexander Mehler and Mevlüt Bagci and Alexander Henlein and Giuseppe Abrami and Christian Spiekermann and Patrick Schrottenbacher and Maxim Konca and Andy Lücking and Juliane Engel and Marc Quintino and Jakob Schreiber and Kevin Saukel and Olga Zlatkin-Troitschanskaia}, title = {A Multimodal Data Model for Simulation-based Learning with {Va.Si.Li-Lab}}, booktitle = {Proceedings of {HCI} International 2023}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2023}, note = {accpeted}, }
-
A. Henlein, “Toward context-based text-to-3D scene generation,” doctoralthesis PhD Thesis, 2023.
[BibTeX]@phdthesis{Henlein:2023, author = {Alexander Henlein}, title = {Toward context-based text-to-3D scene generation}, type = {doctoralthesis}, pages = {199}, school = {Johann Wolfgang Goethe-Universität}, doi = {10.21248/gups.73448}, year = {2023}, pdf = {https://publikationen.ub.uni-frankfurt.de/files/73448/main.pdf} }
-
A. Henlein, A. Gopinath, N. Krishnaswamy, A. Mehler, and J. Pustejovsky, “Grounding human-object interaction to affordance behavior in multimodal datasets,” Frontiers in Artificial Intelligence, vol. 6, 2023.
[BibTeX]@article{Henlein:et:al:2023a, author = {Henlein, Alexander and Gopinath, Anju and Krishnaswamy, Nikhil and Mehler, Alexander and Pustejovsky, James}, doi = {10.3389/frai.2023.1084740}, issn = {2624-8212}, journal = {Frontiers in Artificial Intelligence}, title = {Grounding human-object interaction to affordance behavior in multimodal datasets}, url = {https://www.frontiersin.org/articles/10.3389/frai.2023.1084740}, volume = {6}, year = {2023} }
-
A. Henlein, A. Kett, Baumartz Daniel, G. Abrami, A. Mehler, J. Bastian, Y. Blecher, D. Budgenhagen, R. Christof, T. Ewald, T. Fauerbach, P. Masny, J. Mende, P. Schnüre, and M. Viel, “Semantic Scene Builder: Towards a context sensitive Text-to-3D Scene Framework,” in Semantic, artificial and computational interaction studies: Towards a behavioromics of multimodal communication, Held as Part of the 25rd HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23– 28, 2023, Proceedings, 2023. accepted
[BibTeX]@inproceedings{Henlein:et:al:2023b, author = {Henlein, Alexander and Kett, Attila and Baumartz, Daniel, and Abrami, Giuseppe and Mehler, Alexander and Bastian, Johannes and Blecher, Yannic and Budgenhagen, David and Christof, Roman and Ewald, Tim-Oliver and Fauerbach, Tim and Masny, Patrick and Mende, Julian and Schn{\"u}re, Paul and Viel, Marc}, booktitle = {Semantic, artificial and computational interaction studies: Towards a behavioromics of multimodal communication, Held as Part of the 25rd HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23-- 28, 2023, Proceedings}, note = {accepted}, organization = {Springer}, title = {Semantic Scene Builder: Towards a context sensitive Text-to-3D Scene Framework}, year = {2023} }
2022 (11)
-
C. Ebert, A. Lücking, and A. Mehler, “Introduction to the 2nd Edition of “Semantic, Artificial and Computational Interaction Studies”,” in HCI International 2022 – Late Breaking Papers. Multimodality in Advanced Interaction Environments, Cham, 2022, pp. 36-47.
[Abstract] [BibTeX]``Behavioromics'' is a term that has been invented to cover the study of multimodal interaction from various disciplines and points of view. These disciplines and points of view, however, lack a platform for exchange. The workshop session on ``Semantic, artificial and computational interaction studies'' provides such a platform. We motivate behavioromics, sketch its historical background, and summarize this year's contributions.
@inproceedings{Ebert:et:al:2022, abstract = "``Behavioromics'' is a term that has been invented to cover the study of multimodal interaction from various disciplines and points of view. These disciplines and points of view, however, lack a platform for exchange. The workshop session on ``Semantic, artificial and computational interaction studies'' provides such a platform. We motivate behavioromics, sketch its historical background, and summarize this year's contributions.", address = "Cham", author = "Ebert, Cornelia and L{\"u}cking, Andy and Mehler, Alexander", booktitle = "HCI International 2022 - Late Breaking Papers. Multimodality in Advanced Interaction Environments", editor = "Kurosu, Masaaki and Yamamoto, Sakae and Mori, Hirohiko and Schmorrow, Dylan D. and Fidopiastis, Cali M. and Streitz, Norbert A. and Konomi, Shin'ichi", isbn = "978-3-031-17618-0", pages = "36--47", publisher = "Springer Nature Switzerland", title = "Introduction to the 2nd Edition of ``Semantic, Artificial and Computational Interaction Studies''", doi = {https://doi.org/10.1007/978-3-031-17618-0_3}, year = "2022" }
-
S. Ahmed, R. van der Goot, M. Rehman, C. Kruse, Ö. Özsoy, A. Mehler, and G. Roig, “Tafsir Dataset: A Novel Multi-Task Benchmark for Named Entity Recognition and Topic Modeling in Classical Arabic Literature,” in Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea, 2022, pp. 3753-3768.
[Abstract] [BibTeX]Various historical languages, which used to be lingua franca of science and arts, deserve the attention of current NLP research. In this work, we take the first data-driven steps towards this research line for Classical Arabic (CA) by addressing named entity recognition (NER) and topic modeling (TM) on the example of CA literature. We manually annotate the encyclopedic work of Tafsir Al-Tabari with span-based NEs, sentence-based topics, and span-based subtopics, thus creating the Tafsir Dataset with over 51,000 sentences, the first large-scale multi-task benchmark for CA. Next, we analyze our newly generated dataset, which we make open-source available, with current language models (lightweight BiLSTM, transformer-based MaChAmP) along a novel script compression method, thereby achieving state-of-the-art performance for our target task CA-NER. We also show that CA-TM from the perspective of historical topic models, which are central to Arabic studies, is very challenging. With this interdisciplinary work, we lay the foundations for future research on automatic analysis of CA literature.
@inproceedings{Ahmed:et:al:2022, title = "Tafsir Dataset: A Novel Multi-Task Benchmark for Named Entity Recognition and Topic Modeling in Classical {A}rabic Literature", author = {Ahmed, Sajawel and van der Goot, Rob and Rehman, Misbahur and Kruse, Carl and {\"O}zsoy, {\"O}mer and Mehler, Alexander and Roig, Gemma}, booktitle = "Proceedings of the 29th International Conference on Computational Linguistics", month = oct, year = "2022", address = "Gyeongju, Republic of Korea", publisher = "International Committee on Computational Linguistics", url = "https://aclanthology.org/2022.coling-1.330", pages = "3753--3768", abstract = "Various historical languages, which used to be lingua franca of science and arts, deserve the attention of current NLP research. In this work, we take the first data-driven steps towards this research line for Classical Arabic (CA) by addressing named entity recognition (NER) and topic modeling (TM) on the example of CA literature. We manually annotate the encyclopedic work of Tafsir Al-Tabari with span-based NEs, sentence-based topics, and span-based subtopics, thus creating the Tafsir Dataset with over 51,000 sentences, the first large-scale multi-task benchmark for CA. Next, we analyze our newly generated dataset, which we make open-source available, with current language models (lightweight BiLSTM, transformer-based MaChAmP) along a novel script compression method, thereby achieving state-of-the-art performance for our target task CA-NER. We also show that CA-TM from the perspective of historical topic models, which are central to Arabic studies, is very challenging. With this interdisciplinary work, we lay the foundations for future research on automatic analysis of CA literature.", }
-
J. Ginzburg and A. Lücking, “The Integrated Model of Memory: A Dialogical Perspective,” in Proceedings of SemDial 2022, 2022, pp. 6-17.
[BibTeX]@inproceedings{Ginzburg:Luecking:2022:a, author = {Ginzburg, Jonathan and L{\"u}cking, Andy}, booktitle = {Proceedings of SemDial 2022}, editor = {Gregoromichelaki, Eleni and Hough, Julian and Kelleher, John D.}, location = {Dublin, Ireland}, pages = {6--17}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2022/09/Ginzburg_Luecking-IMM-Dialogue.pdf}, series = {SemDial 2022 -- DubDial}, title = {The Integrated Model of Memory: {A} Dialogical Perspective}, year = 2022 }
-
A. Lücking and J. Ginzburg, “Leading voices: Dialogue semantics, cognitive science, and the polyphonic structure of multimodal interaction,” Language and Cognition, 2022.
[BibTeX]@Article{Luecking:Ginzburg:2022:b, title = {Leading voices: {Dialogue} semantics, cognitive science, and the polyphonic structure of multimodal interaction}, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, journal = {Language and Cognition}, year = 2022, doi = {10.1017/langcog.2022.30}, }
-
A. Lücking and J. Ginzburg, “How to repair a slip of the tongue?,” in Proceedings of SemDial 2022, 2022, pp. 35-46.
[BibTeX]@inproceedings{Luecking:Ginzburg:2022:a, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, booktitle = {Proceedings of SemDial 2022}, editor = {Gregoromichelaki, Eleni and Hough, Julian and Kelleher, John D.}, location = {Dublin, Ireland}, pages = {35--46}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2022/09/Luecking_Ginzburg-SoT.pdf}, series = {SemDial 2022 -- DubDial}, title = {How to repair a slip of the tongue?}, year = 2022 }
-
M. Konca, A. Lücking, A. Mehler, M. Nagel, and O. Zlatkin-Troitschanskaia, Computational educational linguistics for `Critical Online Reasoning’ among young professionals in medicine, law and teaching, 2022.
[BibTeX]@misc{Konca:et:al:2022, author = {Konca, Maxim and L{\"u}cking, Andy and Mehler, Alexander and Nagel, Marie-Theres and Zlatkin-Troitschanskaia, Olga}, howpublished = {Presentation given at the AERA annual meeting, 21.-26.04. 2022, WERA symposium}, month = 04, title = {Computational educational linguistics for `Critical Online Reasoning' among young professionals in medicine, law and teaching}, year = 2022, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2022/10/BRIDGE_WERA_AERA-2022_reduce.pdf} }
-
A. Lücking and J. Ginzburg, “Referential transparency as the proper treatment of quantification,” Semantics and Pragmatics, vol. 15, 2022.
[BibTeX]@Article{Luecking:Ginzburg:2022, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, title = {Referential transparency as the proper treatment of quantification}, journal = {Semantics and Pragmatics}, year = 2022, volume = 15, eid = 4, doi = {10.3765/sp.15.4} }
-
A. Mehler, M. Konca, M. Nagel, A. Lücking, and O. Zlatkin-Troitschanskaia, On latent domain-specific textual preferences in solving Internet-based generic tasks among graduates/young professionals from three domains, 2022.
[Abstract] [BibTeX]Although Critical Online Reasoning (COR) is often viewed as a general competency (e.g. Alexander et al. 2016), studies have found evidence supporting their domain-specificity (Toplak et al. 2002). To investigate this assumption, we focus on commonalities and differences in textual preferences in solving COR-related tasks between graduates/young professionals from three domains. For this reason, we collected data by requiring participants to solve domain-specific (DOM-COR) and generic (GEN-COR) tasks in an authentic Internet-based COR performance assessment (CORA), allowing us to disentangle the assumed components of COR abilities. Here, we focus on GEN-COR to distinguish between different groups of graduates from the three disciplines in the context of generic COR tasks. We present a computational model for educationally relevant texts that combines features at multiple levels (lexical, syntactic, semantic). We use machine learning to predict domain-specific group membership based on documents consulted during task solving. A major contribution of our analyses is a multi-part text classification system that contrasts human annotation and rating of the documents used with a semi-automatic classification to predict the document type of web pages. That is, we work with competing classifications to support our findings. In this way, we develop a computational linguistic model that correlates GEN-COR abilities with properties of documents consulted for solving the GEN-COR tasks. Results show that participants from different domains indeed inquire different sets of online sources for the same task. Machine learning-based classifications show that the distributional differences can be reproduced by computational linguistic models.
@misc{Mehler:et:al:2022, author = {Mehler, Alexander and Konca, Maxim and Nagel, Marie-Theres and L\"{u}cking, Andy and Zlatkin-Troitschanskaia, Olga}, year = {2022}, month = {03}, howpublished = {Presentation at BEBF 2022}, title = {On latent domain-specific textual preferences in solving Internet-based generic tasks among graduates/young professionals from three domains}, abstract={Although Critical Online Reasoning (COR) is often viewed as a general competency (e.g. Alexander et al. 2016), studies have found evidence supporting their domain-specificity (Toplak et al. 2002). To investigate this assumption, we focus on commonalities and differences in textual preferences in solving COR-related tasks between graduates/young professionals from three domains. For this reason, we collected data by requiring participants to solve domain-specific (DOM-COR) and generic (GEN-COR) tasks in an authentic Internet-based COR performance assessment (CORA), allowing us to disentangle the assumed components of COR abilities. Here, we focus on GEN-COR to distinguish between different groups of graduates from the three disciplines in the context of generic COR tasks. We present a computational model for educationally relevant texts that combines features at multiple levels (lexical, syntactic, semantic). We use machine learning to predict domain-specific group membership based on documents consulted during task solving. A major contribution of our analyses is a multi-part text classification system that contrasts human annotation and rating of the documents used with a semi-automatic classification to predict the document type of web pages. That is, we work with competing classifications to support our findings. In this way, we develop a computational linguistic model that correlates GEN-COR abilities with properties of documents consulted for solving the GEN-COR tasks. Results show that participants from different domains indeed inquire different sets of online sources for the same task. Machine learning-based classifications show that the distributional differences can be reproduced by computational linguistic models.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2022/04/On_latent_domain-specific_textual_preferences_in_solving_Internet-based_generic_tasks_among_graduates__young_professionals_from_three_domains.pdf} }
-
A. Henlein and A. Mehler, “What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured,” in Proceedings of the 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022), 2022. accepted
[BibTeX]@InProceedings{Henlein:Mehler:2022, Author = {Henlein, Alexander and Mehler, Alexander}, Title = {What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured}, BookTitle = {Proceedings of the 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)}, location = {Seattle, Washington}, year = 2022, note = {accepted} }
-
G. Abrami, M. Bagci, L. Hammerla, and A. Mehler, “German Parliamentary Corpus (GerParCor),” in Proceedings of the Language Resources and Evaluation Conference, Marseille, France, 2022, pp. 1900-1906.
[Abstract] [Poster][BibTeX]Parliamentary debates represent a large and partly unexploited treasure trove of publicly accessible texts. In the German-speaking area, there is a certain deficit of uniformly accessible and annotated corpora covering all German-speaking parliaments at the national and federal level. To address this gap, we introduce the German Parliamentary Corpus (GerParCor). GerParCor is a genre-specific corpus of (predominantly historical) German-language parliamentary protocols from three centuries and four countries, including state and federal level data. In addition, GerParCor contains conversions of scanned protocols and, in particular, of protocols in Fraktur converted via an OCR process based on Tesseract. All protocols were preprocessed by means of the NLP pipeline of spaCy3 and automatically annotated with metadata regarding their session date. GerParCor is made available in the XMI format of the UIMA project. In this way, GerParCor can be used as a large corpus of historical texts in the field of political communication for various tasks in NLP.
@InProceedings{Abrami:Bagci:Hammerla:Mehler:2022, author = {Abrami, Giuseppe and Bagci, Mevlüt and Hammerla, Leon and Mehler, Alexander}, title = {German Parliamentary Corpus (GerParCor)}, booktitle = {Proceedings of the Language Resources and Evaluation Conference}, month = {June}, year = {2022}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {1900--1906}, abstract = {Parliamentary debates represent a large and partly unexploited treasure trove of publicly accessible texts. In the German-speaking area, there is a certain deficit of uniformly accessible and annotated corpora covering all German-speaking parliaments at the national and federal level. To address this gap, we introduce the German Parliamentary Corpus (GerParCor). GerParCor is a genre-specific corpus of (predominantly historical) German-language parliamentary protocols from three centuries and four countries, including state and federal level data. In addition, GerParCor contains conversions of scanned protocols and, in particular, of protocols in Fraktur converted via an OCR process based on Tesseract. All protocols were preprocessed by means of the NLP pipeline of spaCy3 and automatically annotated with metadata regarding their session date. GerParCor is made available in the XMI format of the UIMA project. In this way, GerParCor can be used as a large corpus of historical texts in the field of political communication for various tasks in NLP.}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2022/06/GerParCor_LREC_2022.pdf}, pdf = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.202.pdf} }
-
A. Lücking, M. Stoeckel, G. Abrami, and A. Mehler, “I still have Time(s): Extending HeidelTime for German Texts,” in Proceedings of the Language Resources and Evaluation Conference, Marseille, France, 2022, pp. 4723-4728.
[Abstract] [Poster][BibTeX]HeidelTime is one of the most widespread and successful tools for detecting temporal expressions in texts. Since HeidelTime’s pattern matching system is based on regular expression, it can be extended in a convenient way. We present such an extension for the German resources of HeidelTime: HeidelTimeExt. The extension has been brought about by means of observing false negatives within real world texts and various time banks. The gain in coverage is 2.7 \% or 8.5 \%, depending on the admitted degree of potential overgeneralization. We describe the development of HeidelTimeExt, its evaluation on text samples from various genres, and share some linguistic observations. HeidelTimeExt can be obtained from https://github.com/texttechnologylab/heideltime.
@InProceedings{Luecking:Stoeckel:Abrami:Mehler:2022, Author = {L\"{u}cking, Andy and Stoeckel, Manuel and Abrami, Giuseppe and Mehler, Alexander}, title = {I still have Time(s): Extending HeidelTime for German Texts}, booktitle = {Proceedings of the Language Resources and Evaluation Conference}, month = {June}, year = {2022}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {4723--4728}, abstract = {HeidelTime is one of the most widespread and successful tools for detecting temporal expressions in texts. Since HeidelTime’s pattern matching system is based on regular expression, it can be extended in a convenient way. We present such an extension for the German resources of HeidelTime: HeidelTimeExt. The extension has been brought about by means of observing false negatives within real world texts and various time banks. The gain in coverage is 2.7 \% or 8.5 \%, depending on the admitted degree of potential overgeneralization. We describe the development of HeidelTimeExt, its evaluation on text samples from various genres, and share some linguistic observations. HeidelTimeExt can be obtained from https://github.com/texttechnologylab/heideltime.}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2022/06/HeidelTimeExt_LREC_2022.pdf}, pdf = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.505.pdf} }
2021 (15)
-
M. Konca, A. Mehler, D. Baumartz, and W. Hemati, “From distinguishability to informativity. A quantitative text model for detecting random texts.,” Language and Text: Data, models, information and applications, vol. 356, pp. 145-162, 2021.
[BibTeX]@article{Konca:et:al:2021, title={From distinguishability to informativity. A quantitative text model for detecting random texts.}, author={Konca, Maxim and Mehler, Alexander and Baumartz, Daniel and Hemati, Wahed}, journal={Language and Text: Data, models, information and applications}, volume={356}, pages={145--162}, year={2021}, editor={Adam Paw{\l}owski, Jan Ma{\v{c}}utek, Sheila Embleton and George Mikros}, publisher={John Benjamins Publishing Company}, doi={10.1075/cilt.356.10kon} }
-
T. Lokot, O. Abramov, and A. Mehler, “On the asymptotic behavior of the average geodesic distance L and the compactness CB of simple connected undirected graphs whose order approaches infinity,” PLOS ONE, vol. 16, iss. 11, pp. 1-13, 2021.
[Abstract] [BibTeX]The average geodesic distance L Newman (2003) and the compactness CB Botafogo (1992) are important graph indices in applications of complex network theory to real-world problems. Here, for simple connected undirected graphs G of order n, we study the behavior of L(G) and CB(G), subject to the condition that their order |V(G)| approaches infinity. We prove that the limit of L(G)/n and CB(G) lies within the interval [0;1/3] and [2/3;1], respectively. Moreover, for any not necessarily rational number β ∈ [0;1/3] (α ∈ [2/3;1]) we show how to construct the sequence of graphs G, |V(G)| = n → ∞, for which the limit of L(G)/n (CB(G)) is exactly β (α) (Theorems 1 and 2). Based on these results, our work points to novel classification possibilities of graphs at the node level as well as to the information-theoretic classification of the structural complexity of graph indices.
@article{Lokot:Abramov:Mehler:2021, doi = {10.1371/journal.pone.0259776}, author = {Lokot, Tatiana and Abramov, Olga and Mehler, Alexander}, journal = {PLOS ONE}, publisher = {Public Library of Science}, title = {On the asymptotic behavior of the average geodesic distance L and the compactness CB of simple connected undirected graphs whose order approaches infinity}, year = {2021}, month = {11}, volume = {16}, url = {https://doi.org/10.1371/journal.pone.0259776}, pages = {1-13}, abstract = {The average geodesic distance L Newman (2003) and the compactness CB Botafogo (1992) are important graph indices in applications of complex network theory to real-world problems. Here, for simple connected undirected graphs G of order n, we study the behavior of L(G) and CB(G), subject to the condition that their order |V(G)| approaches infinity. We prove that the limit of L(G)/n and CB(G) lies within the interval [0;1/3] and [2/3;1], respectively. Moreover, for any not necessarily rational number β ∈ [0;1/3] (α ∈ [2/3;1]) we show how to construct the sequence of graphs {G}, |V(G)| = n → ∞, for which the limit of L(G)/n (CB(G)) is exactly β (α) (Theorems 1 and 2). Based on these results, our work points to novel classification possibilities of graphs at the node level as well as to the information-theoretic classification of the structural complexity of graph indices.}, number = {11} }
-
A. Mehler, D. Baumartz, and T. Uslu, “SemioGraphs: Visualizing Topic Networks as Mulit-Codal Graphs,” in International Quantitative Linguistics Conference (QUALICO 2021), 2021.
[Poster][BibTeX]@InProceedings{Mehler:Uslu:Baumartz:2021, Author = {Mehler, Alexander and Baumartz, Daniel and Uslu, Tolga}, Title = {{SemioGraphs:} Visualizing Topic Networks as Mulit-Codal Graphs}, BookTitle = {International Quantitative Linguistics Conference (QUALICO 2021)}, Series = {QUALICO 2021}, location = {Tokyo, Japan}, year = {2021}, poster = {https://www.texttechnologylab.org/files/Qualico_2021_Semiograph_Poster.pdf} }
-
A. Lücking, J. Ginzburg, and R. Cooper, “Grammar in dialogue,” in Head Driven Phrase Structure Grammar: The handbook, S. Müller, A. Abeillé, R. D. Borsley, and J. Koenig, Eds., Berlin: Language Science Press, 2021, pp. 1155-1199.
[BibTeX]@InCollection{Luecking:Ginzburg:Cooper:2021, author = {L\"{u}cking, Andy and Ginzburg, Jonathan and Cooper, Robin}, year = 2021, title = {Grammar in dialogue}, chapter = {26}, pages = {1155-1199}, url = {https://langsci-press.org/catalog/book/259}, editor = {M{\"u}ller, Stefan and Abeill{\'e}, Anne and Borsley, Robert D. and Koenig, Jean-Pierre}, booktitle = {{Head Driven Phrase Structure Grammar: The handbook}}, year = 2021, series = {Empirically Oriented Theoretical Morphology and Syntax}, number = 9, address = {Berlin}, publisher = {Language Science Press}, doi = {10.5281/zenodo.5543318} }
-
A. Lücking, “Gesture,” in Head Driven Phrase Structure Grammar: The handbook, S. Müller, A. Abeillé, R. D. Borsley, and J. Koenig, Eds., Berlin: Language Science Press, 2021, pp. 1201-1250.
[BibTeX]@InCollection{Luecking:2021, author = {L\"{u}cking, Andy}, title = {Gesture}, pages = {1201-1250}, chapter = {27}, url = {https://langsci-press.org/catalog/book/259}, editor = {M{\"u}ller, Stefan and Abeill{\'e}, Anne and Borsley, Robert D. and Koenig, Jean-Pierre}, booktitle = {{Head Driven Phrase Structure Grammar: The handbook}}, year = 2021, series = {Empirically Oriented Theoretical Morphology and Syntax}, number = 9, address = {Berlin}, publisher = {Language Science Press}, doi = {10.5281/zenodo.5543318} }
-
A. Lücking and J. Ginzburg, “Saying and shaking `No’,” in Proceedings of the 28th International Conference on Head-Driven Phrase Structure Grammar, Online (Frankfurt/Main), Frankfurt/Main, 2021, pp. 283-299.
[BibTeX]@InProceedings{Luecking:Ginzburg:2021:a, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, title = {Saying and shaking `No'}, booktitle = {{Proceedings of the 28th International Conference on Head-Driven Phrase Structure Grammar, Online (Frankfurt/Main)}}, editor = {M{\"u}ller, Stefan and Melnik, Nurit}, issn = {1535-1793}, doi = {10.21248/hpsg.2021.15}, publisher = {University Library}, address = {Frankfurt/Main}, pages = {283--299}, year = 2021, }
-
J. Ginzburg and A. Lücking, “Requesting clarifications with speech and gestures,” in Beyond Language: Multimodal Semantic Representations, 2021.
[BibTeX]@InProceedings{Ginzburg:Luecking:2021:a, title = {Requesting clarifications with speech and gestures}, author = {Ginzburg, Jonathan and L{\"u}cking, Andy}, booktitle = {Beyond Language: Multimodal Semantic Representations}, series = {MMSR I}, year = 2021, location = {Virtually at the University of Groningen, held in conjuction with IWCS 2021}, url = {https://iwcs2021.github.io/proceedings/mmsr/pdf/2021.mmsr-1.3.pdf} }
-
J. Ginzburg and A. Lücking, “I thought pointing is rude: A dialogue-semantic analysis of pointing at the addressee,” in Proceedings of \textitSinn und Bedeutung 25, 2021, pp. 276-291. Special Session: Gestures and Natural Language Semantics
[BibTeX]@InProceedings{Ginzburg:Luecking:2021:b, author = {Ginzburg, Jonathan and L{\"u}cking, Andy}, title = {I thought pointing is rude: {A} dialogue-semantic analysis of pointing at the addressee}, booktitle = {Proceedings of \textit{Sinn und Bedeutung 25}}, series = {SuB 25}, year = 2021, pages = {276-291}, editor = {Grosz, Patrick and Mart{\'i}, Luisa and Pearson, Hazel and Sudo, Yasutada and Zobel, Sarah}, note = {Special Session: Gestures and Natural Language Semantics}, location = {University College London (Online)}, url = {https://ojs.ub.uni-konstanz.de/sub/index.php/sub/article/view/937} }
-
A. Henlein, G. Abrami, A. Kett, C. Spiekermann, and A. Mehler, “Digital Learning, Teaching and Collaboration in an Era of ubiquitous Quarantine,” in Remote Learning in Times of Pandemic – Issues, Implications and Best Practice, L. Daniela and A. Visvizin, Eds., Thames, Oxfordshire, England, UK: Routledge, 2021.
[BibTeX]@incollection{Henlein:et:al:2021, author = {Alexander Henlein and Giuseppe Abrami and Attila Kett and Christian Spiekermann and Alexander Mehler}, title = {Digital Learning, Teaching and Collaboration in an Era of ubiquitous Quarantine}, editor = "Linda Daniela and Anna Visvizin", booktitle = "Remote Learning in Times of Pandemic - Issues, Implications and Best Practice", publisher = "Routledge", address = "Thames, Oxfordshire, England, UK", year = 2021, chapter = 3 }
-
A. Lücking, C. Driller, M. Stoeckel, G. Abrami, A. Pachzelt, and A. Mehler, “Multiple Annotation for Biodiversity: Developing an annotation framework among biology, linguistics and text technology,” Language Resources and Evaluation, 2021.
[BibTeX]@Article{Luecking:et:al:2021, author = {Andy Lücking and Christine Driller and Manuel Stoeckel and Giuseppe Abrami and Adrian Pachzelt and Alexander Mehler}, year = {2021}, journal = {Language Resources and Evaluation}, title = {Multiple Annotation for Biodiversity: Developing an annotation framework among biology, linguistics and text technology}, editor = {Nancy Ide and Nicoletta Calzolari}, doi = {10.1007/s10579-021-09553-5}, pdf = {https://link.springer.com/content/pdf/10.1007/s10579-021-09553-5.pdf} }
-
P. Fischer, A. Smajic, G. Abrami, and A. Mehler, “Multi-Type-TD-TSR – Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations,” in Proceedings of the 44th German Conference on Artificial Intelligence, 2021.
[BibTeX]@InProceedings{Fischer:et:al:2021, Author = {Fischer, Pascal and Smajic, Alen and Abrami, Giuseppe and Mehler, Alexander}, Title = {Multi-Type-TD-TSR - Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations}, BookTitle = {Proceedings of the 44th German Conference on Artificial Intelligence}, Series = {KI2021}, location = {Berlin, Germany}, year = {2021}, url = {https://www.springerprofessional.de/multi-type-td-tsr-extracting-tables-from-document-images-using-a/19711570}, pdf = {https://arxiv.org/pdf/2105.11021.pdf} }
-
M. Klement, A. Henlein, and A. Mehler, “VoxML Annotation Tool Review and Suggestions for Improvement,” in Proceedings of the Seventeenth Joint ACL – ISO Workshop on Interoperable Semantic Annotation (ISA-17, Note for special track on visual information annotation), 2021.
[BibTeX]@InProceedings{Klement:et:al:2021, Author = {Klement, Mark and Henlein, Alexander and Mehler, Alexander}, Title = {VoxML Annotation Tool Review and Suggestions for Improvement}, BookTitle = {Proceedings of the Seventeenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation (ISA-17, Note for special track on visual information annotation)}, Series = {ISA-17}, location = {Groningen, Netherlands}, month = {June}, year = {2021}, pdf = {https://sigsem.uvt.nl/isa17/32_Klement-Paper.pdf} }
-
G. Abrami, A. Henlein, A. Lücking, A. Kett, P. Adeberg, and A. Mehler, “Unleashing annotations with TextAnnotator: Multimedia, multi-perspective document views for ubiquitous annotation,” in Proceedings of the Seventeenth Joint ACL – ISO Workshop on Interoperable Semantic Annotation (ISA-17), 2021.
[BibTeX]@InProceedings{Abrami:et:al:2021, Author = {Abrami, Giuseppe and Henlein, Alexander and Lücking, Andy and Kett, Attila and Adeberg, Pascal and Mehler, Alexander}, Title = {Unleashing annotations with {TextAnnotator}: Multimedia, multi-perspective document views for ubiquitous annotation}, BookTitle = {Proceedings of the Seventeenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation (ISA-17)}, Series = {ISA-17}, location = {Groningen, Netherlands}, month = {June}, year = {2021}, pdf = {https://iwcs2021.github.io/proceedings/isa/pdf/2021.isa-1.7.pdf} }
-
A. Lücking, S. Brückner, G. Abrami, T. Uslu, and A. Mehler, “Computational linguistic assessment of textbooks and online texts by means of threshold concepts in economics,” Frontiers in Education, 2021.
[BibTeX]@article{Luecking:Brueckner:Abrami:Uslu:Mehler:2021, journal = {Frontiers in Education}, doi = {10.3389/feduc.2020.578475}, title = {Computational linguistic assessment of textbooks and online texts by means of threshold concepts in economics}, author = {L{\"u}cking, Andy and Br{\"u}ckner, Sebastian and Abrami, Giuseppe and Uslu, Tolga and Mehler, Alexander}, eid = {578475}, url = {https://www.frontiersin.org/articles/10.3389/feduc.2020.578475/}, year = {2021} }
-
A. Mehler, D. Baumartz, and T. Uslu, “SemioGraphs: Visualizing Topic Networks as Mulit-Codal Graphs,” in International Quantitative Linguistics Conference (QUALICO 2021), 2021.
[BibTeX]@InProceedings{Mehler:Uslu:Baumartz:2021, Author = {Mehler, Alexander and Baumartz, Daniel and Uslu, Tolga}, Title = {{SemioGraphs:} Visualizing Topic Networks as Mulit-Codal Graphs}, BookTitle = {International Quantitative Linguistics Conference (QUALICO 2021)}, Series = {QUALICO 2021}, location = {Tokyo, Japan}, year = {2021} }
2020 (20)
-
T. Uslu, “Multi-document analysis : semantic analysis of large text corpora beyond topic modeling,” PhD Thesis, 2020.
[BibTeX]@phdthesis{Uslu:2020, author = {Tolga Uslu}, title = {Multi-document analysis : semantic analysis of large text corpora beyond topic modeling}, pages = {204}, year = {2020}, url = {http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56140}, pdf = {http://publikationen.ub.uni-frankfurt.de/files/56140/Dissertation_Tolga_Uslu.pdf} }
-
W. Hemati, “TextImager-VSD : large scale verb sense disambiguation and named entity recognition in the context of TextImager,” PhD Thesis, 2020.
[BibTeX]@phdthesis{Hemati:2020, author = {Wahed Hemati}, title = {TextImager-VSD : large scale verb sense disambiguation and named entity recognition in the context of TextImager}, pages = {174}, year = {2020}, url = {http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56089}, pdf = {http://publikationen.ub.uni-frankfurt.de/files/56089/dissertation_Wahed_Hemati.pdf} }
-
A. Mehler, W. Hemati, P. Welke, M. Konca, and T. Uslu, “Multiple Texts as a Limiting Factor in Online Learning: Quantifying (Dis-)similarities of Knowledge Networks,” Frontiers in Education, vol. 5, p. 206, 2020.
[Abstract] [BibTeX]We test the hypothesis that the extent to which one obtains information on a given topic through Wikipedia depends on the language in which it is consulted. Controlling the size factor, we investigate this hypothesis for a number of 25 subject areas. Since Wikipedia is a central part of the web-based information landscape, this indicates a language-related, linguistic bias. The article therefore deals with the question of whether Wikipedia exhibits this kind of linguistic relativity or not. From the perspective of educational science, the article develops a computational model of the information landscape from which multiple texts are drawn as typical input of web-based reading. For this purpose, it develops a hybrid model of intra- and intertextual similarity of different parts of the information landscape and tests this model on the example of 35 languages and corresponding Wikipedias. In the way it measures the similarities of hypertexts, the article goes beyond existing approaches by examining their structural and semantic aspects intra- and intertextually. In this way it builds a bridge between reading research, educational science, Wikipedia research and computational linguistics.
@article{Mehler:Hemati:Welke:Konca:Uslu:2020, abstract = {We test the hypothesis that the extent to which one obtains information on a given topic through Wikipedia depends on the language in which it is consulted. Controlling the size factor, we investigate this hypothesis for a number of 25 subject areas. Since Wikipedia is a central part of the web-based information landscape, this indicates a language-related, linguistic bias. The article therefore deals with the question of whether Wikipedia exhibits this kind of linguistic relativity or not. From the perspective of educational science, the article develops a computational model of the information landscape from which multiple texts are drawn as typical input of web-based reading. For this purpose, it develops a hybrid model of intra- and intertextual similarity of different parts of the information landscape and tests this model on the example of 35 languages and corresponding Wikipedias. In the way it measures the similarities of hypertexts, the article goes beyond existing approaches by examining their structural and semantic aspects intra- and intertextually. In this way it builds a bridge between reading research, educational science, Wikipedia research and computational linguistics.}, author = {Mehler, Alexander and Hemati, Wahed and Welke, Pascal and Konca, Maxim and Uslu, Tolga}, doi = {10.3389/feduc.2020.562670}, issn = {2504-284X}, journal = {Frontiers in Education}, pages = {206}, title = {Multiple Texts as a Limiting Factor in Online Learning: Quantifying (Dis-)similarities of Knowledge Networks}, url = {https://www.frontiersin.org/article/10.3389/feduc.2020.562670}, pdf = {https://www.frontiersin.org/articles/10.3389/feduc.2020.562670/pdf}, volume = {5}, year = {2020} }
-
A. Lücking, S. Brückner, G. Abrami, T. Uslu, and A. Mehler, “Computational linguistic assessment of textbook and online learning media by means of threshold concepts in business education,” CoRR, vol. abs/2008.02096, 2020.
[BibTeX]@article{Luecking:et:al:2020, author = {Andy L{\"{u}}cking and Sebastian Br{\"{u}}ckner and Giuseppe Abrami and Tolga Uslu and Alexander Mehler}, title = {Computational linguistic assessment of textbook and online learning media by means of threshold concepts in business education}, journal = {CoRR}, volume = {abs/2008.02096}, year = {2020}, url = {https://arxiv.org/abs/2008.02096}, archivePrefix = {arXiv}, eprint = {2008.02096}, timestamp = {Fri, 07 Aug 2020 15:07:21 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-02096.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
-
D. Baumartz, “Automatic Topic Modeling in the Context of Digital Libraries: Mehrsprachige Korpus-basierte Erweiterung von text2ddc – eine experimentelle Studie,” , 2020.
[BibTeX]@thesis{Baumartz:2020, author = {Baumartz, Daniel}, title = {{Automatic Topic Modeling in the Context of Digital Libraries: Mehrsprachige Korpus-basierte Erweiterung von text2ddc - eine experimentelle Studie}}, year = 2020, month = 6, type = {bathesis}, school = {Johann Wolfgang Goethe-Universität, Institute of Computer Science and Mathematics, Text Technology Lab}, address = {Frankfurt, Germany}, url = {https://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56381}, pdf = {https://publikationen.ub.uni-frankfurt.de/files/56381/baumartz_bachelorarbeit_2020_pub.pdf} }
-
C. Driller, M. Koch, G. Abrami, W. Hemati, A. Lücking, A. Mehler, A. Pachzelt, and G. Kasperek, “Fast and Easy Access to Central European Biodiversity Data with BIOfid,” Biodiversity Information Science and Standards, vol. 4, p. e59157, 2020.
[Abstract] [BibTeX]The storage of data in public repositories such as the Global Biodiversity Information Facility (GBIF) or the National Center for Biotechnology Information (NCBI) is nowadays stipulated in the policies of many publishers in order to facilitate data replication or proliferation. Species occurrence records contained in legacy printed literature are no exception to this. The extent of their digital and machine-readable availability, however, is still far from matching the existing data volume (Thessen and Parr 2014). But precisely these data are becoming more and more relevant to the investigation of ongoing loss of biodiversity. In order to extract species occurrence records at a larger scale from available publications, one has to apply specialised text mining tools. However, such tools are in short supply especially for scientific literature in the German language.The Specialised Information Service Biodiversity Research*1 BIOfid (Koch et al. 2017) aims at reducing this desideratum, inter alia, by preparing a searchable text corpus semantically enriched by a new kind of multi-label annotation. For this purpose, we feed manual annotations into automatic, machine-learning annotators. This mixture of automatic and manual methods is needed, because BIOfid approaches a new application area with respect to language (mainly German of the 19th century), text type (biological reports), and linguistic focus (technical and everyday language).We will present current results of the performance of BIOfid’s semantic search engine and the application of independent natural language processing (NLP) tools. Most of these are freely available online, such as TextImager (Hemati et al. 2016). We will show how TextImager is tied into the BIOfid pipeline and how it is made scalable (e.g. extendible by further modules) and usable on different systems (docker containers).Further, we will provide a short introduction to generating machine-learning training data using TextAnnotator (Abrami et al. 2019) for multi-label annotation. Annotation reproducibility can be assessed by the implementation of inter-annotator agreement methods (Abrami et al. 2020). Beyond taxon recognition and entity linking, we place particular emphasis on location and time information. For this purpose, our annotation tag-set combines general categories and biology-specific categories (including taxonomic names) with location and time ontologies. The application of the annotation categories is regimented by annotation guidelines (Lücking et al. 2020). Within the next years, our work deliverable will be a semantically accessible and data-extractable text corpus of around two million pages. In this way, BIOfid is creating a new valuable resource that expands our knowledge of biodiversity and its determinants.
@article{Driller:et:al:2020, author = {Christine Driller and Markus Koch and Giuseppe Abrami and Wahed Hemati and Andy Lücking and Alexander Mehler and Adrian Pachzelt and Gerwin Kasperek}, title = {Fast and Easy Access to Central European Biodiversity Data with BIOfid}, volume = {4}, number = {}, year = {2020}, doi = {10.3897/biss.4.59157}, publisher = {Pensoft Publishers}, abstract = {The storage of data in public repositories such as the Global Biodiversity Information Facility (GBIF) or the National Center for Biotechnology Information (NCBI) is nowadays stipulated in the policies of many publishers in order to facilitate data replication or proliferation. Species occurrence records contained in legacy printed literature are no exception to this. The extent of their digital and machine-readable availability, however, is still far from matching the existing data volume (Thessen and Parr 2014). But precisely these data are becoming more and more relevant to the investigation of ongoing loss of biodiversity. In order to extract species occurrence records at a larger scale from available publications, one has to apply specialised text mining tools. However, such tools are in short supply especially for scientific literature in the German language.The Specialised Information Service Biodiversity Research*1 BIOfid (Koch et al. 2017) aims at reducing this desideratum, inter alia, by preparing a searchable text corpus semantically enriched by a new kind of multi-label annotation. For this purpose, we feed manual annotations into automatic, machine-learning annotators. This mixture of automatic and manual methods is needed, because BIOfid approaches a new application area with respect to language (mainly German of the 19th century), text type (biological reports), and linguistic focus (technical and everyday language).We will present current results of the performance of BIOfid’s semantic search engine and the application of independent natural language processing (NLP) tools. Most of these are freely available online, such as TextImager (Hemati et al. 2016). We will show how TextImager is tied into the BIOfid pipeline and how it is made scalable (e.g. extendible by further modules) and usable on different systems (docker containers).Further, we will provide a short introduction to generating machine-learning training data using TextAnnotator (Abrami et al. 2019) for multi-label annotation. Annotation reproducibility can be assessed by the implementation of inter-annotator agreement methods (Abrami et al. 2020). Beyond taxon recognition and entity linking, we place particular emphasis on location and time information. For this purpose, our annotation tag-set combines general categories and biology-specific categories (including taxonomic names) with location and time ontologies. The application of the annotation categories is regimented by annotation guidelines (Lücking et al. 2020). Within the next years, our work deliverable will be a semantically accessible and data-extractable text corpus of around two million pages. In this way, BIOfid is creating a new valuable resource that expands our knowledge of biodiversity and its determinants.}, issn = {}, pages = {e59157}, URL = {https://doi.org/10.3897/biss.4.59157}, eprint = {https://doi.org/10.3897/biss.4.59157}, journal = {Biodiversity Information Science and Standards} }
-
J. Ginzburg and A. Lücking, “On Laughter and Forgetting and Reconversing: A neurologically-inspired model of conversational context,” in Proceedings of The 24th Workshop on the Semantics and Pragmatics of Dialogue, 2020.
[BibTeX]@InProceedings{Ginzburg:Luecking:2020:a, author = {Ginzburg, Jonathan and L{\"u}cking, Andy}, title = {On Laughter and Forgetting and Reconversing: A neurologically-inspired model of conversational context}, booktitle = {Proceedings of The 24th Workshop on the Semantics and Pragmatics of Dialogue}, series = {SemDial/WatchDial}, year = 2020, location = {Brandeis University, Waltham (Watch City), MA}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2020/08/dia-with-mem-semdial20.pdf} }
-
A. Lücking and J. Ginzburg, “Towards the score of communication,” in Proceedings of The 24th Workshop on the Semantics and Pragmatics of Dialogue, 2020.
[BibTeX]@InProceedings{Luecking:Ginzburg:2020, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, title = {Towards the score of communication}, booktitle = {Proceedings of The 24th Workshop on the Semantics and Pragmatics of Dialogue}, series = {SemDial/WatchDial}, year = 2020, location = {Brandeis University, Waltham (Watch City), MA}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2020/08/comm-scores-semdial20.pdf} }
-
G. Abrami, A. Mehler, and M. Stoeckel, “TextAnnotator: A web-based annotation suite for texts,” in Proceedings of the Digital Humanities 2020, 2020.
[Abstract] [Poster][BibTeX]The TextAnnotator is a tool for simultaneous and collaborative annotation of texts with visual annotation support, integration of knowledge bases and, by pipelining the TextImager, a rich variety of pre-processing and automatic annotation tools. It includes a variety of modules for the annotation of texts, which contains the annotation of argumentative, rhetorical, propositional and temporal structures as well as a module for named entity linking and rapid annotation of named entities. Especially the modules for annotation of temporal, argumentative and propositional structures are currently unique in web-based annotation tools. The TextAnnotator, which allows the annotation of texts as a platform, is divided into a front- and a backend component. The backend is a web service based on WebSockets, which integrates the UIMA Database Interface to manage and use texts. Texts are made accessible by using the ResourceManager and the AuthorityManager, based on user and group access permissions. Different views of a document can be created and used depending on the scenario. Once a document has been opened, access is gained to the annotations stored within annotation views in which these are organized. Any annotation view can be assigned with access permissions and by default, each user obtains his or her own user view for every annotated document. In addition, with sufficient access permissions, all annotation views can also be used and curated. This allows the possibility to calculate an Inter-Annotator-Agreement for a document, which shows an agreement between the annotators. Annotators without sufficient rights cannot display this value so that the annotators do not influence each other. This contribution is intended to reflect the current state of development of TextAnnotator, demonstrate the possibilities of an instantaneous Inter-Annotator-Agreement and trigger a discussion about further functions for the community.
@InProceedings{Abrami:Mehler:Stoeckel:2020, author = {Abrami, Giuseppe and Mehler, Alexander and Stoeckel, Manuel}, title = {{TextAnnotator}: A web-based annotation suite for texts}, booktitle = {Proceedings of the Digital Humanities 2020}, series = {DH 2020}, location = {Ottawa, Canada}, year = {2020}, url = {https://dh2020.adho.org/wp-content/uploads/2020/07/547_TextAnnotatorAwebbasedannotationsuitefortexts.html}, doi = {http://dx.doi.org/10.17613/tenm-4907}, abstract = {The TextAnnotator is a tool for simultaneous and collaborative annotation of texts with visual annotation support, integration of knowledge bases and, by pipelining the TextImager, a rich variety of pre-processing and automatic annotation tools. It includes a variety of modules for the annotation of texts, which contains the annotation of argumentative, rhetorical, propositional and temporal structures as well as a module for named entity linking and rapid annotation of named entities. Especially the modules for annotation of temporal, argumentative and propositional structures are currently unique in web-based annotation tools. The TextAnnotator, which allows the annotation of texts as a platform, is divided into a front- and a backend component. The backend is a web service based on WebSockets, which integrates the UIMA Database Interface to manage and use texts. Texts are made accessible by using the ResourceManager and the AuthorityManager, based on user and group access permissions. Different views of a document can be created and used depending on the scenario. Once a document has been opened, access is gained to the annotations stored within annotation views in which these are organized. Any annotation view can be assigned with access permissions and by default, each user obtains his or her own user view for every annotated document. In addition, with sufficient access permissions, all annotation views can also be used and curated. This allows the possibility to calculate an Inter-Annotator-Agreement for a document, which shows an agreement between the annotators. Annotators without sufficient rights cannot display this value so that the annotators do not influence each other. This contribution is intended to reflect the current state of development of TextAnnotator, demonstrate the possibilities of an instantaneous Inter-Annotator-Agreement and trigger a discussion about further functions for the community.}, poster = {https://hcommons.org/deposits/download/hc:31816/CONTENT/dh2020_textannotator_poster.pdf} }
-
G. Abrami, M. Stoeckel, and A. Mehler, “TextAnnotator: A UIMA Based Tool for the Simultaneous and Collaborative Annotation of Texts,” in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, 2020, pp. 891-900.
[Abstract] [BibTeX]The annotation of texts and other material in the field of digital humanities and Natural Language Processing (NLP) is a common task of research projects. At the same time, the annotation of corpora is certainly the most time- and cost-intensive component in research projects and often requires a high level of expertise according to the research interest. However, for the annotation of texts, a wide range of tools is available, both for automatic and manual annotation. Since the automatic pre-processing methods are not error-free and there is an increasing demand for the generation of training data, also with regard to machine learning, suitable annotation tools are required. This paper defines criteria of flexibility and efficiency of complex annotations for the assessment of existing annotation tools. To extend this list of tools, the paper describes TextAnnotator, a browser-based, multi-annotation system, which has been developed to perform platform-independent multimodal annotations and annotate complex textual structures. The paper illustrates the current state of development of TextAnnotator and demonstrates its ability to evaluate annotation quality (inter-annotator agreement) at runtime. In addition, it will be shown how annotations of different users can be performed simultaneously and collaboratively on the same document from different platforms using UIMA as the basis for annotation.
@InProceedings{Abrami:Stoeckel:Mehler:2020, author = {Abrami, Giuseppe and Stoeckel, Manuel and Mehler, Alexander}, title = {TextAnnotator: A UIMA Based Tool for the Simultaneous and Collaborative Annotation of Texts}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {891--900}, ISBN = "979-10-95546-34-4", abstract = {The annotation of texts and other material in the field of digital humanities and Natural Language Processing (NLP) is a common task of research projects. At the same time, the annotation of corpora is certainly the most time- and cost-intensive component in research projects and often requires a high level of expertise according to the research interest. However, for the annotation of texts, a wide range of tools is available, both for automatic and manual annotation. Since the automatic pre-processing methods are not error-free and there is an increasing demand for the generation of training data, also with regard to machine learning, suitable annotation tools are required. This paper defines criteria of flexibility and efficiency of complex annotations for the assessment of existing annotation tools. To extend this list of tools, the paper describes TextAnnotator, a browser-based, multi-annotation system, which has been developed to perform platform-independent multimodal annotations and annotate complex textual structures. The paper illustrates the current state of development of TextAnnotator and demonstrates its ability to evaluate annotation quality (inter-annotator agreement) at runtime. In addition, it will be shown how annotations of different users can be performed simultaneously and collaboratively on the same document from different platforms using UIMA as the basis for annotation.}, url = {https://www.aclweb.org/anthology/2020.lrec-1.112}, pdf = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.112.pdf} }
-
G. Abrami, A. Henlein, A. Kett, and A. Mehler, “Text2SceneVR: Generating Hypertexts with VAnnotatoR as a Pre-processing Step for Text2Scene Systems,” in Proceedings of the 31st ACM Conference on Hypertext and Social Media, New York, NY, USA, 2020, p. 177–186.
[BibTeX]@InProceedings{Abrami:Henlein:Kett:Mehler:2020, author = {Abrami, Giuseppe and Henlein, Alexander and Kett, Attila and Mehler, Alexander}, title = {{Text2SceneVR}: Generating Hypertexts with VAnnotatoR as a Pre-processing Step for Text2Scene Systems}, booktitle = {Proceedings of the 31st ACM Conference on Hypertext and Social Media}, series = {HT ’20}, year = {2020}, location = {Virtual Event, USA}, isbn = {9781450370981}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3372923.3404791}, doi = {10.1145/3372923.3404791}, pages = {177–186}, numpages = {10}, pdf={https://dl.acm.org/doi/pdf/10.1145/3372923.3404791} }
-
M. Stoeckel, A. Henlein, W. Hemati, and A. Mehler, “Voting for POS tagging of Latin texts: Using the flair of FLAIR to better Ensemble Classifiers by Example of Latin,” in Proceedings of LT4HALA 2020 – 1st Workshop on Language Technologies for Historical and Ancient Languages, Marseille, France, 2020, pp. 130-135.
[Abstract] [BibTeX]Despite the great importance of the Latin language in the past, there are relatively few resources available today to develop modern NLP tools for this language. Therefore, the EvaLatin Shared Task for Lemmatization and Part-of-Speech (POS) tagging was published in the LT4HALA workshop. In our work, we dealt with the second EvaLatin task, that is, POS tagging. Since most of the available Latin word embeddings were trained on either few or inaccurate data, we trained several embeddings on better data in the first step. Based on these embeddings, we trained several state-of-the-art taggers and used them as input for an ensemble classifier called LSTMVoter. We were able to achieve the best results for both the cross-genre and the cross-time task (90.64\% and 87.00\%) without using additional annotated data (closed modality). In the meantime, we further improved the system and achieved even better results (96.91\% on classical, 90.87\% on cross-genre and 87.35\% on cross-time).
@InProceedings{Stoeckel:et:al:2020, author = {Stoeckel, Manuel and Henlein, Alexander and Hemati, Wahed and Mehler, Alexander}, title = {{Voting for POS tagging of Latin texts: Using the flair of FLAIR to better Ensemble Classifiers by Example of Latin}}, booktitle = {Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association (ELRA)}, pages = {130--135}, abstract = {Despite the great importance of the Latin language in the past, there are relatively few resources available today to develop modern NLP tools for this language. Therefore, the EvaLatin Shared Task for Lemmatization and Part-of-Speech (POS) tagging was published in the LT4HALA workshop. In our work, we dealt with the second EvaLatin task, that is, POS tagging. Since most of the available Latin word embeddings were trained on either few or inaccurate data, we trained several embeddings on better data in the first step. Based on these embeddings, we trained several state-of-the-art taggers and used them as input for an ensemble classifier called LSTMVoter. We were able to achieve the best results for both the cross-genre and the cross-time task (90.64\% and 87.00\%) without using additional annotated data (closed modality). In the meantime, we further improved the system and achieved even better results (96.91\% on classical, 90.87\% on cross-genre and 87.35\% on cross-time).}, url = {https://www.aclweb.org/anthology/2020.lt4hala-1.21}, pdf = {http://www.lrec-conf.org/proceedings/lrec2020/workshops/LT4HALA/pdf/2020.lt4hala-1.21.pdf} }
-
A. Mehler, B. Jussen, T. Geelhaar, A. Henlein, G. Abrami, D. Baumartz, T. Uslu, and W. Hemati, “The Frankfurt Latin Lexicon. From Morphological Expansion and Word Embeddings to SemioGraphs,” Studi e Saggi Linguistici, vol. 58, iss. 1, pp. 121-155, 2020.
[Abstract] [BibTeX]In this article we present the Frankfurt Latin Lexicon (FLL), a lexical resource for Medieval Latin that is used both for the lemmatization of Latin texts and for the post-editing of lemmatizations. We describe recent advances in the development of lemmatizers and test them against the Capitularies corpus (comprising Frankish royal edicts, mid-6th to mid-9th century), a corpus created as a reference for processing Medieval Latin. We also consider the post-correction of lemmatizations using a limited crowdsourcing process aimed at continuous review and updating of the FLL. Starting from the texts resulting from this lemmatization process, we describe the extension of the FLL by means of word embeddings, whose interactive traversing by means of SemioGraphs completes the digital enhanced hermeneutic circle. In this way, the article argues for a more comprehensive understanding of lemmatization, encompassing classical machine learning as well as intellectual post-corrections and, in particular, human computation in the form of interpretation processes based on graph representations of the underlying lexical resources.
@article{Mehler:et:al:2020b, author={Mehler, Alexander and Jussen, Bernhard and Geelhaar, Tim and Henlein, Alexander and Abrami, Giuseppe and Baumartz, Daniel and Uslu, Tolga and Hemati, Wahed}, title={{The Frankfurt Latin Lexicon. From Morphological Expansion and Word Embeddings to SemioGraphs}}, journal={Studi e Saggi Linguistici}, doi={10.4454/ssl.v58i1.276}, year={2020}, volume={58}, number={1}, pages={121--155}, abstract={In this article we present the Frankfurt Latin Lexicon (FLL), a lexical resource for Medieval Latin that is used both for the lemmatization of Latin texts and for the post-editing of lemmatizations. We describe recent advances in the development of lemmatizers and test them against the Capitularies corpus (comprising Frankish royal edicts, mid-6th to mid-9th century), a corpus created as a reference for processing Medieval Latin. We also consider the post-correction of lemmatizations using a limited crowdsourcing process aimed at continuous review and updating of the FLL. Starting from the texts resulting from this lemmatization process, we describe the extension of the FLL by means of word embeddings, whose interactive traversing by means of SemioGraphs completes the digital enhanced hermeneutic circle. In this way, the article argues for a more comprehensive understanding of lemmatization, encompassing classical machine learning as well as intellectual post-corrections and, in particular, human computation in the form of interpretation processes based on graph representations of the underlying lexical resources.}, url={https://www.studiesaggilinguistici.it/index.php/ssl/article/view/276}, pdf={https://www.studiesaggilinguistici.it/index.php/ssl/article/download/276/219} }
-
A. Henlein, G. Abrami, A. Kett, and A. Mehler, “Transfer of ISOSpace into a 3D Environment for Annotations and Applications,” in Proceedings of the 16th Joint ACL – ISO Workshop on Interoperable Semantic Annotation, Marseille, 2020, pp. 32-35.
[Abstract] [BibTeX]People's visual perception is very pronounced and therefore it is usually no problem for them to describe the space around them in words. Conversely, people also have no problems imagining a concept of a described space. In recent years many efforts have been made to develop a linguistic concept for spatial and spatial-temporal relations. However, the systems have not really caught on so far, which in our opinion is due to the complex models on which they are based and the lack of available training data and automated taggers. In this paper we describe a project to support spatial annotation, which could facilitate annotation by its many functions, but also enrich it with many more information. This is to be achieved by an extension by means of a VR environment, with which spatial relations can be better visualized and connected with real objects. And we want to use the available data to develop a new state-of-the-art tagger and thus lay the foundation for future systems such as improved text understanding for Text2Scene.
@InProceedings{Henlein:et:al:2020, Author = {Henlein, Alexander and Abrami, Giuseppe and Kett, Attila and Mehler, Alexander}, Title = {Transfer of ISOSpace into a 3D Environment for Annotations and Applications}, booktitle = {Proceedings of the 16th Joint ACL - ISO Workshop on Interoperable Semantic Annotation}, month = {May}, year = {2020}, address = {Marseille}, publisher = {European Language Resources Association}, pages = {32--35}, abstract = {People's visual perception is very pronounced and therefore it is usually no problem for them to describe the space around them in words. Conversely, people also have no problems imagining a concept of a described space. In recent years many efforts have been made to develop a linguistic concept for spatial and spatial-temporal relations. However, the systems have not really caught on so far, which in our opinion is due to the complex models on which they are based and the lack of available training data and automated taggers. In this paper we describe a project to support spatial annotation, which could facilitate annotation by its many functions, but also enrich it with many more information. This is to be achieved by an extension by means of a VR environment, with which spatial relations can be better visualized and connected with real objects. And we want to use the available data to develop a new state-of-the-art tagger and thus lay the foundation for future systems such as improved text understanding for Text2Scene.}, url = {https://www.aclweb.org/anthology/2020.isa-1.4}, pdf = {http://www.lrec-conf.org/proceedings/lrec2020/workshops/ISA16/pdf/2020.isa-1.4.pdf} }
-
J. Hildebrand, W. Hemati, and A. Mehler, “Recognizing Sentence-level Logical Document Structures with the Help of Context-free Grammars,” in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, 2020, pp. 5282-5290.
[Abstract] [BibTeX]Current sentence boundary detectors split documents into sequentially ordered sentences by detecting their beginnings and ends. Sentences, however, are more deeply structured even on this side of constituent and dependency structure: they can consist of a main sentence and several subordinate clauses as well as further segments (e.g. inserts in parentheses); they can even recursively embed whole sentences and then contain multiple sentence beginnings and ends. In this paper, we introduce a tool that segments sentences into tree structures to detect this type of recursive structure. To this end, we retrain different constituency parsers with the help of modified training data to transform them into sentence segmenters. With these segmenters, documents are mapped to sequences of sentence-related “logical document structures”. The resulting segmenters aim to improve downstream tasks by providing additional structural information. In this context, we experiment with German dependency parsing. We show that for certain sentence categories, which can be determined automatically, improvements in German dependency parsing can be achieved using our segmenter for preprocessing. The assumption suggests that improvements in other languages and tasks can be achieved.
@InProceedings{Hildebrand:Hemati:Mehler:2020, Author = {Hildebrand, Jonathan and Hemati, Wahed and Mehler, Alexander}, Title = {Recognizing Sentence-level Logical Document Structures with the Help of Context-free Grammars}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {5282--5290}, abstract = {Current sentence boundary detectors split documents into sequentially ordered sentences by detecting their beginnings and ends. Sentences, however, are more deeply structured even on this side of constituent and dependency structure: they can consist of a main sentence and several subordinate clauses as well as further segments (e.g. inserts in parentheses); they can even recursively embed whole sentences and then contain multiple sentence beginnings and ends. In this paper, we introduce a tool that segments sentences into tree structures to detect this type of recursive structure. To this end, we retrain different constituency parsers with the help of modified training data to transform them into sentence segmenters. With these segmenters, documents are mapped to sequences of sentence-related “logical document structures”. The resulting segmenters aim to improve downstream tasks by providing additional structural information. In this context, we experiment with German dependency parsing. We show that for certain sentence categories, which can be determined automatically, improvements in German dependency parsing can be achieved using our segmenter for preprocessing. The assumption suggests that improvements in other languages and tasks can be achieved.}, url = {https://www.aclweb.org/anthology/2020.lrec-1.650}, pdf = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.650.pdf} }
-
A. Henlein and A. Mehler, “On the Influence of Coreference Resolution on Word Embeddings in Lexical-semantic Evaluation Tasks,” in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, 2020, pp. 27-33.
[Abstract] [BibTeX]Coreference resolution (CR) aims to find all spans of a text that refer to the same entity. The F1-Scores on these task have been greatly improved by new developed End2End-approaches and transformer networks. The inclusion of CR as a pre-processing step is expected to lead to improvements in downstream tasks. The paper examines this effect with respect to word embeddings. That is, we analyze the effects of CR on six different embedding methods and evaluate them in the context of seven lexical-semantic evaluation tasks and instantiation/hypernymy detection. Especially in the last tasks we hoped for a significant increase in performance. We show that all word embedding approaches do not benefit significantly from pronoun substitution. The measurable improvements are only marginal (around 0.5\% in most test cases). We explain this result with the loss of contextual information, reduction of the relative occurrence of rare words and the lack of pronouns to be replaced.
@InProceedings{Henlein:Mehler:2020, Author = {Henlein, Alexander and Mehler, Alexander}, Title = {{On the Influence of Coreference Resolution on Word Embeddings in Lexical-semantic Evaluation Tasks}}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {27--33}, abstract = {Coreference resolution (CR) aims to find all spans of a text that refer to the same entity. The F1-Scores on these task have been greatly improved by new developed End2End-approaches and transformer networks. The inclusion of CR as a pre-processing step is expected to lead to improvements in downstream tasks. The paper examines this effect with respect to word embeddings. That is, we analyze the effects of CR on six different embedding methods and evaluate them in the context of seven lexical-semantic evaluation tasks and instantiation/hypernymy detection. Especially in the last tasks we hoped for a significant increase in performance. We show that all word embedding approaches do not benefit significantly from pronoun substitution. The measurable improvements are only marginal (around 0.5\% in most test cases). We explain this result with the loss of contextual information, reduction of the relative occurrence of rare words and the lack of pronouns to be replaced.}, url = {https://www.aclweb.org/anthology/2020.lrec-1.4}, pdf = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.4.pdf} }
-
A. Mehler, R. Gleim, R. Gaitsch, T. Uslu, and W. Hemati, “From Topic Networks to Distributed Cognitive Maps: Zipfian Topic Universes in the Area of Volunteered Geographic Information,” Complexity, vol. 4, pp. 1-47, 2020.
[BibTeX]@Article{Mehler:Gleim:Gaitsch:Uslu:Hemati:2020, author = {Alexander Mehler and R{\"{u}}diger Gleim and Regina Gaitsch and Tolga Uslu and Wahed Hemati}, title = {From Topic Networks to Distributed Cognitive Maps: {Zipfian} Topic Universes in the Area of Volunteered Geographic Information}, journal = {Complexity}, volume = {4}, doi={10.1155/2020/4607025}, pages = {1-47}, issuetitle = {Cognitive Network Science: A New Frontier}, year = {2020}, }
-
V. Kühn, G. Abrami, and A. Mehler, “WikNectVR: A Gesture-Based Approach for Interacting in Virtual Reality Based on WikNect and Gestural Writing,” in Virtual, Augmented and Mixed Reality. Design and Interaction – 12th International Conference, VAMR 2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Copenhagen, Denmark, July 19-24, 2020, Proceedings, Part I, 2020, pp. 299-312.
[BibTeX]@inproceedings{Kuehn:Abrami:Mehler:2020, author = {Vincent K{\"{u}}hn and Giuseppe Abrami and Alexander Mehler}, editor = {Jessie Y. C. Chen and Gino Fragomeni}, title = {WikNectVR: {A} Gesture-Based Approach for Interacting in Virtual Reality Based on WikNect and Gestural Writing}, booktitle = {Virtual, Augmented and Mixed Reality. Design and Interaction - 12th International Conference, {VAMR} 2020, Held as Part of the 22nd {HCI} International Conference, {HCII} 2020, Copenhagen, Denmark, July 19-24, 2020, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {12190}, pages = {299--312}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-49695-1_20}, doi = {10.1007/978-3-030-49695-1_20}, timestamp = {Tue, 14 Jul 2020 10:55:57 +0200}, biburl = {https://dblp.org/rec/conf/hci/KuhnAM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
-
G. Abrami, A. Mehler, C. Spiekermann, A. Kett, S. Lööck, and L. Schwarz, “Educational Technologies in the area of ubiquitous historical computing in virtual reality,” in New Perspectives on Virtual and Augmented Reality: Finding New Ways to Teach in a Transformed Learning Environment, L. Daniela, Ed., Taylor & Francis, 2020.
[Abstract] [BibTeX]At ever shorter intervals, new technologies are being developed that are opening up more and more areas of application. This regards, for example, Virtual Reality (VR) and Augmented Reality (AR) devices. In addition to the private sector, the public and education sectors, which already make intensive use of these devices, benefit from these technologies. However, especially in the field of historical education, there are not many frameworks for generating immersive virtual environments that can be used flexibly enough. This chapter addresses this gap by means of VAnnotatoR. VAnnotatoR is a versatile framework for the creation and use of virtual environments that serve to model historical processes in historical education. The paper describes the building blocks of VAnnotatoR and describes applications in historical education.
@InBook{Abrami:et:al:2020, author="Abrami, Giuseppe and Mehler, Alexander and Spiekermann, Christian and Kett, Attila and L{\"o}{\"o}ck, Simon and Schwarz, Lukas", editor="Daniela, Linda", title="Educational Technologies in the area of ubiquitous historical computing in virtual reality", bookTitle="New Perspectives on Virtual and Augmented Reality: Finding New Ways to Teach in a Transformed Learning Environment", year="2020", publisher="Taylor \& Francis", abstract="At ever shorter intervals, new technologies are being developed that are opening up more and more areas of application. This regards, for example, Virtual Reality (VR) and Augmented Reality (AR) devices. In addition to the private sector, the public and education sectors, which already make intensive use of these devices, benefit from these technologies. However, especially in the field of historical education, there are not many frameworks for generating immersive virtual environments that can be used flexibly enough. This chapter addresses this gap by means of VAnnotatoR. VAnnotatoR is a versatile framework for the creation and use of virtual environments that serve to model historical processes in historical education. The paper describes the building blocks of VAnnotatoR and describes applications in historical education.", isbn={978-0-367-43211-9}, url={https://www.routledge.com/New-Perspectives-on-Virtual-and-Augmented-Reality-Finding-New-Ways-to-Teach/Daniela/p/book/9780367432119} }
-
C. Stegbauer and A. Mehler, “Ursachen der Entstehung von ubiquitären Zentrum-Peripheriestrukturen und ihre Folgen,” Soziale Welt — Zeitschrift für sozialwissenschaftliche Forschung und Praxis (SozW), vol. Sonderband 23, pp. 265-284, 2020.
[BibTeX]@Article{Stegbauer:Mehler:2020, author = {Christian Stegbauer and Alexander Mehler}, title = {Ursachen der Entstehung von ubiquit{\"{a}}ren Zentrum-Peripheriestrukturen und ihre Folgen}, journal = {Soziale Welt -- Zeitschrift f\"{u}r sozialwissenschaftliche Forschung und Praxis (SozW)}, volume = {Sonderband 23}, year = {2020}, pages = {265--284} }
2019 (25)
-
O. Zlatkin-Troitschanskaia, W. Bisang, A. Mehler, M. Banerjee, and J. Roeper, “Positive Learning in the Internet Age: Developments and Perspectives in the PLATO Program,” in Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO), O. Zlatkin-Troitschanskaia, Ed., Cham: Springer International Publishing, 2019, pp. 1-5.
[Abstract] [BibTeX]The Internet has become the main informational entity, i.e., a public source of information. The Internet offers many new benefits and opportunities for human learning, teaching, and research. However, by providing a vast amount of information from innumerable sources, it also enables the manipulation of information; there are countless examples of disseminated misinformation and false data in mass and social media. Much of the information presented online is conflicting, preselected, or algorithmically obscure, often colliding with fundamental humanistic values and posing moral or ethical problems.
@Inbook{Zlatkin-Troitschanskaia:et:al:2019, author="Zlatkin-Troitschanskaia, Olga and Bisang, Walter and Mehler, Alexander and Banerjee, Mita and Roeper, Jochen", editor="Zlatkin-Troitschanskaia, Olga", title="Positive Learning in the Internet Age: Developments and Perspectives in the PLATO Program", bookTitle="Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO)", year="2019", publisher="Springer International Publishing", address="Cham", pages="1--5", abstract="The Internet has become the main informational entity, i.e., a public source of information. The Internet offers many new benefits and opportunities for human learning, teaching, and research. However, by providing a vast amount of information from innumerable sources, it also enables the manipulation of information; there are countless examples of disseminated misinformation and false data in mass and social media. Much of the information presented online is conflicting, preselected, or algorithmically obscure, often colliding with fundamental humanistic values and posing moral or ethical problems.", isbn="978-3-030-26578-6", doi="10.1007/978-3-030-26578-6_1", url="https://doi.org/10.1007/978-3-030-26578-6_1" }
-
A. Mehler and V. Ramesh, “TextInContext: On the Way to a Framework for Measuring the Context-Sensitive Complexity of Educationally Relevant Texts—A Combined Cognitive and Computational Linguistic Approach,” in Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO), O. Zlatkin-Troitschanskaia, Ed., Cham: Springer International Publishing, 2019, pp. 167-195.
[Abstract] [BibTeX]We develop a framework for modeling the context sensitivity of text interpretation. As a point of reference, we focus on the complexity of educational texts. To open up a broader basis for representing phenomena of context sensitivity, we integrate a learning theory (i.e., the Cognitive Load Theory) with a theory of discourse comprehension (i.e., the Construction Integration Model) and a theory of cognitive semantics (i.e., the theory of Conceptual Spaces). The aim is to construct measures that view text complexity as a relational attribute by analogy to the relational concept of meaning in situation semantics. To this end, we reconstruct the situation semantic notion of relational meaning from the perspective of a computationally informed cognitive semantics. The aim is to prepare the development of measurements for predicting learning outcomes in the form of positive or negative learning. This prediction ideally depends on the underlying learning material, the learner's situational context, and knowledge retrieved from his or her long-term memory, which he or she uses to arrive at coherent mental representations of the underlying texts. Finally, our model refers to machine learning as a tool for modeling such memory content. In this way, the chapter integrates approaches from different disciplines (linguistic semantics, computational linguistics, cognitive science, and data science).
@Inbook{Mehler:Ramesh:2019, author="Mehler, Alexander and Ramesh, Visvanathan", editor="Zlatkin-Troitschanskaia, Olga", title="{TextInContext}: On the Way to a Framework for Measuring the Context-Sensitive Complexity of Educationally Relevant Texts---A Combined Cognitive and Computational Linguistic Approach", bookTitle="Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO)", year="2019", publisher="Springer International Publishing", address="Cham", pages="167--195", abstract="We develop a framework for modeling the context sensitivity of text interpretation. As a point of reference, we focus on the complexity of educational texts. To open up a broader basis for representing phenomena of context sensitivity, we integrate a learning theory (i.e., the Cognitive Load Theory) with a theory of discourse comprehension (i.e., the Construction Integration Model) and a theory of cognitive semantics (i.e., the theory of Conceptual Spaces). The aim is to construct measures that view text complexity as a relational attribute by analogy to the relational concept of meaning in situation semantics. To this end, we reconstruct the situation semantic notion of relational meaning from the perspective of a computationally informed cognitive semantics. The aim is to prepare the development of measurements for predicting learning outcomes in the form of positive or negative learning. This prediction ideally depends on the underlying learning material, the learner's situational context, and knowledge retrieved from his or her long-term memory, which he or she uses to arrive at coherent mental representations of the underlying texts. Finally, our model refers to machine learning as a tool for modeling such memory content. In this way, the chapter integrates approaches from different disciplines (linguistic semantics, computational linguistics, cognitive science, and data science).", isbn="978-3-030-26578-6", doi="10.1007/978-3-030-26578-6_14", url="https://doi.org/10.1007/978-3-030-26578-6_14" }
-
A. Lücking, “Dialogue semantics: From cognitive structures to positive and negative learning,” in Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO), O. Zlatkin-Troitschankskaia, Ed., Cham, Switzerland: Springer Nature Switzerland AG, 2019, pp. 197-205.
[BibTeX]@InCollection{Luecking:2019:a, author = {L\"{u}cking, Andy}, title = {Dialogue semantics: {From} cognitive structures to positive and negative learning}, year = 2019, pages = {197-205}, publisher = {Springer Nature Switzerland AG}, address = {Cham, Switzerland}, editor = {Zlatkin-Troitschankskaia, Olga}, booktitle = {Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO)}, doi = {10.1007/978-3-030-26578-6}, url = {https://link.springer.com/chapter/10.1007/978-3-030-26578-6_15} }
-
A. Lücking and J. Ginzburg, “Not few but all quantifiers can be negated: towards a referentially transparent semantics of quantified noun phrases,” in Proceedings of the Amsterdam Colloquium 2019, 2019, pp. 269-278.
[BibTeX]@InProceedings{Luecking:Ginzburg:2019, author = {L{\"u}cking, Andy and Ginzburg, Jonathan}, title = {Not few but all quantifiers can be negated: towards a referentially transparent semantics of quantified noun phrases}, booktitle = {Proceedings of the Amsterdam Colloquium 2019}, series = {AC'19}, location = {University of Amsterdam}, year = 2019, pages = {269-278}, url = {http://events.illc.uva.nl/AC/AC2019/}, pdf = {http://events.illc.uva.nl/AC/AC2019/uploaded_files/inlineitem/L_cking_and_Ginzburg_Not_few_but_all_quantifiers_ca.pdf} }
-
A. Lücking, “Gesture,” in Head-Driven Phrase Structure Grammar: The handbook, S. Müller, A. Abeillé, R. D. Borsley, and J. Koenig, Eds., Berlin: Language Science Press, 2019.
[BibTeX]@InCollection{Luecking:2019:b, keywords = {own,bookchapter}, author+an = {1=highlight}, author = {L\"{u}cking, Andy}, year = 2019, title = {Gesture}, editor = {M\"{u}ller, Stefan and Abeill\'{e}, Anne and Borsley, Robert D. and Koenig, Jean-Pierre}, booktitle = {{Head-Driven Phrase Structure Grammar}: {The} handbook}, address = {Berlin}, publisher = {Language Science Press}, pdf = {https://hpsg.hu-berlin.de/Projects/HPSG-handbook/PDFs/gesture.pdf}, url = {https://langsci-press.org/catalog/book/259} }
-
A. Lücking, J. Ginzburg, and R. Cooper, “Grammar in dialogue,” in Head-Driven Phrase Structure Grammar: The handbook, S. Müller, A. Abeillé, R. D. Borsley, and J. Koenig, Eds., Berlin: Language Science Press, 2019.
[BibTeX]@InCollection{Luecking:Ginzburg:Cooper:2019, keywords = {own,bookchapter}, author+an = {1=highlight}, author = {L\"{u}cking, Andy and Ginzburg, Jonathan and Cooper, Robin}, year = 2019, title = {Grammar in dialogue}, editor = {M\"{u}ller, Stefan and Abeill\'{e}, Anne and Borsley, Robert D. and Koenig, Jean-Pierre}, booktitle = {{Head-Driven Phrase Structure Grammar}: {The} handbook}, address = {Berlin}, publisher = {Language Science Press}, pdf = {https://hpsg.hu-berlin.de/Projects/HPSG-handbook/PDFs/dialogue.pdf}, url = {https://langsci-press.org/catalog/book/259} }
-
S. Schweter and S. Ahmed, “Deep-EOS: General-Purpose Neural Networks for Sentence Boundary Detection,” in Proceedings of the 15th Conference on Natural Language Processing (KONVENS), 2019.
[BibTeX]@InProceedings{Schweter:Ahmed:2019, author = {Stefan Schweter and Sajawel Ahmed}, title = {{Deep-EOS: General-Purpose Neural Networks for Sentence Boundary Detection}}, booktitle = {Proceedings of the 15th Conference on Natural Language Processing (KONVENS)}, location = {Erlangen, Germany}, year = 2019 }
-
M. Stoeckel, W. Hemati, and A. Mehler, “When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in Spanish,” in Proceedings of The 5th Workshop on BioNLP Open Shared Tasks, Hong Kong, China, 2019, pp. 11-15.
[Abstract] [BibTeX]The recognition of pharmacological substances, compounds and proteins is an essential preliminary work for the recognition of relations between chemicals and other biomedically relevant units. In this paper, we describe an approach to Task 1 of the PharmaCoNER Challenge, which involves the recognition of mentions of chemicals and drugs in Spanish medical texts. We train a state-of-the-art BiLSTM-CRF sequence tagger with stacked Pooled Contextualized Embeddings, word and sub-word embeddings using the open-source framework FLAIR. We present a new corpus composed of articles and papers from Spanish health science journals, termed the Spanish Health Corpus, and use it to train domain-specific embeddings which we incorporate in our model training. We achieve a result of 89.76\% F1-score using pre-trained embeddings and are able to improve these results to 90.52\% F1-score using specialized embeddings.
@inproceedings{Stoeckel:Hemati:Mehler:2019, title = "When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in {S}panish", author = "Stoeckel, Manuel and Hemati, Wahed and Mehler, Alexander", booktitle = "Proceedings of The 5th Workshop on BioNLP Open Shared Tasks", month = nov, year = "2019", address = "Hong Kong, China", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D19-5702", doi = "10.18653/v1/D19-5702", pages = "11--15", abstract = "The recognition of pharmacological substances, compounds and proteins is an essential preliminary work for the recognition of relations between chemicals and other biomedically relevant units. In this paper, we describe an approach to Task 1 of the PharmaCoNER Challenge, which involves the recognition of mentions of chemicals and drugs in Spanish medical texts. We train a state-of-the-art BiLSTM-CRF sequence tagger with stacked Pooled Contextualized Embeddings, word and sub-word embeddings using the open-source framework FLAIR. We present a new corpus composed of articles and papers from Spanish health science journals, termed the Spanish Health Corpus, and use it to train domain-specific embeddings which we incorporate in our model training. We achieve a result of 89.76{\%} F1-score using pre-trained embeddings and are able to improve these results to 90.52{\%} F1-score using specialized embeddings.", }
-
S. Ahmed, M. Stoeckel, C. Driller, A. Pachzelt, and Alexander Mehler, “BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature,” in Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Hong Kong, China, 2019, pp. 871-880.
[Abstract] [BibTeX]The Specialized Information Service Biodiversity Research (BIOfid) has been launched to mobilize valuable biological data from printed literature hidden in German libraries for over the past 250 years. In this project, we annotate German texts converted by OCR from historical scientific literature on the biodiversity of plants, birds, moths and butterflies. Our work enables the automatic extraction of biological information previously buried in the mass of papers and volumes. For this purpose, we generated training data for the tasks of Named Entity Recognition (NER) and Taxa Recognition (TR) in biological documents. We use this data to train a number of leading machine learning tools and create a gold standard for TR in biodiversity literature. More specifically, we perform a practical analysis of our newly generated BIOfid dataset through various downstream-task evaluations and establish a new state of the art for TR with 80.23\% F-score. In this sense, our paper lays the foundations for future work in the field of information extraction in biology texts.
@InProceedings{Ahmed:Stoeckel:Driller:Pachzelt:Mehler:2019, author = {Sajawel Ahmed and Manuel Stoeckel and Christine Driller and Adrian Pachzelt and Alexander Mehler}, title = {{BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature}}, booktitle = {Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)}, publisher = {Association for Computational Linguistics}, year = 2019, booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)", address = "Hong Kong, China", url = "https://www.aclweb.org/anthology/K19-1081", doi = "10.18653/v1/K19-1081", pages = "871--880", abstract = "The Specialized Information Service Biodiversity Research (BIOfid) has been launched to mobilize valuable biological data from printed literature hidden in German libraries for over the past 250 years. In this project, we annotate German texts converted by OCR from historical scientific literature on the biodiversity of plants, birds, moths and butterflies. Our work enables the automatic extraction of biological information previously buried in the mass of papers and volumes. For this purpose, we generated training data for the tasks of Named Entity Recognition (NER) and Taxa Recognition (TR) in biological documents. We use this data to train a number of leading machine learning tools and create a gold standard for TR in biodiversity literature. More specifically, we perform a practical analysis of our newly generated BIOfid dataset through various downstream-task evaluations and establish a new state of the art for TR with 80.23{\%} F-score. In this sense, our paper lays the foundations for future work in the field of information extraction in biology texts.", }
-
A. Mehler and G. Abrami, “VAnnotatoR: A framework for the multimodal reconstruction of historical situations and spaces,” in Proceedings of the Time Machine Conference, Dresden, Germany, October 10-11 2019.
[Poster][BibTeX]@inproceedings{Mehler:Abrami:2019, author = {Mehler, Alexander and Abrami, Giuseppe}, title = {{VAnnotatoR}: A framework for the multimodal reconstruction of historical situations and spaces}, booktitle = {Proceedings of the Time Machine Conference}, year = {2019}, date = {October 10-11}, address = {Dresden, Germany}, poster={https://www.texttechnologylab.org/wp-content/uploads/2019/09/TimeMachineConference.pdf} }
-
A. Hunziker, H. Mammadov, W. Hemati, and A. Mehler, “Corpus2Wiki: A MediaWiki-based Tool for Automatically Generating Wikiditions in Digital Humanities,” in INF-DH-2019, Bonn, 2019.
[BibTeX]@inproceedings{Hunziker:et:al:2019, author = {Hunziker, Alex and Mammadov, Hasanagha and Hemati, Wahed and Mehler, Alexander}, title = {{Corpus2Wiki}: A MediaWiki-based Tool for Automatically Generating Wikiditions in Digital Humanities}, booktitle = {INF-DH-2019}, year = {2019}, editor = {Burghardt, Manuel AND Müller-Birn, Claudia}, publisher = {Gesellschaft für Informatik e.V.}, address = {Bonn} }
-
A. Hoenen, “Rooting through Direction — New and Old Approaches,” in DHd 2019, 2019.
[BibTeX]@InProceedings{Hoenen:2019dhd, Author = {Hoenen, Armin}, Title = {{Rooting through Direction -- New and Old Approaches}}, BookTitle = {DHd 2019}, url = {https://zenodo.org/record/2596095#.XKtQb3Wg-vo}, year = 2019, month = {jun} }
-
A. Hoenen, “Interpreting and Post-Correcting the Minimum Spanning Tree,” in DGfS 2019, 2019.
[BibTeX]@InProceedings{Hoenen:2019dgfs, Author = {Hoenen, Armin}, Title = {{Interpreting and Post-Correcting the Minimum Spanning Tree}}, BookTitle = {DGfS 2019}, url = {http://www.dgfs2019.uni-bremen.de/abstracts/poster/Hoenen.pdf}, year = 2019 }
-
A. Hoenen, “eLearning the URLCoFi – Digital Didactics for Humanists,” in AIUCD 2019, 2019.
[BibTeX]@InProceedings{Hoenen:2019aiucd, Author = {Hoenen, Armin}, Title = {{eLearning the URLCoFi – Digital Didactics for Humanists}}, BookTitle = {AIUCD 2019}, url = {http://aiucd2019.uniud.it/wp-content/uploads/2019/01/BoA-2019_PROVV.pdf}, year = 2019 }
-
A. Lücking, R. Cooper, S. Larsson, and J. Ginzburg, “Distribution is not enough — Going Firther,” in Proceedings of Natural Language and Computer Science, 2019.
[BibTeX]@InProceedings{Luecking:Cooper:Larsson:Ginzburg:2019, author = {Lücking, Andy and Cooper, Robin and Larsson, Staffan and Ginzburg, Jonathan}, title = {Distribution is not enough -- Going {Firther}}, booktitle = {Proceedings of Natural Language and Computer Science}, maintitle = {The 13th International Conference on Computational Semantics (IWCS 2019)}, series = {NLCS 6}, location = {Gothenburg, Sweden}, month = {May}, year = 2019, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/05/Distribution_is_not_enough.pdf} }
-
W. Hemati and A. Mehler, “CRFVoter: gene and protein related object recognition using a conglomerate of CRF-based tools,” Journal of Cheminformatics, vol. 11, iss. 1, p. 11, 2019.
[Abstract] [BibTeX]Gene and protein related objects are an important class of entities in biomedical research, whose identification and extraction from scientific articles is attracting increasing interest. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of gene and protein related objects. For this purpose, we transform the task as posed by BioCreative V.5 into a sequence labeling problem. We present a series of sequence labeling systems that we used and adapted in our experiments for solving this task. Our experiments show how to optimize the hyperparameters of the classifiers involved. To this end, we utilize various algorithms for hyperparameter optimization. Finally, we present CRFVoter, a two-stage application of Conditional Random Field (CRF) that integrates the optimized sequence labelers from our study into one ensemble classifier.
@article{Hemati:Mehler:2019b, author="Hemati, Wahed and Mehler, Alexander", title="{{CRFVoter}: gene and protein related object recognition using a conglomerate of CRF-based tools}", journal={Journal of Cheminformatics}, year="2019", month="Mar", day="14", volume="11", number="1", pages="11", abstract="Gene and protein related objects are an important class of entities in biomedical research, whose identification and extraction from scientific articles is attracting increasing interest. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of gene and protein related objects. For this purpose, we transform the task as posed by BioCreative V.5 into a sequence labeling problem. We present a series of sequence labeling systems that we used and adapted in our experiments for solving this task. Our experiments show how to optimize the hyperparameters of the classifiers involved. To this end, we utilize various algorithms for hyperparameter optimization. Finally, we present CRFVoter, a two-stage application of Conditional Random Field (CRF) that integrates the optimized sequence labelers from our study into one ensemble classifier.", issn="1758-2946", doi="10.1186/s13321-019-0343-x", url="https://doi.org/10.1186/s13321-019-0343-x" }
-
G. Abrami, A. Mehler, A. Lücking, E. Rieb, and P. Helfrich, “TextAnnotator: A flexible framework for semantic annotations,” in Proceedings of the Fifteenth Joint ACL – ISO Workshop on Interoperable Semantic Annotation, (ISA-15), 2019.
[Abstract] [BibTeX]Modern annotation tools should meet at least the following general requirements: they can handle diverse data and annotation levels within one tool, and they support the annotation process with automatic (pre-)processing outcomes as much as possible. We developed a framework that meets these general requirements and that enables versatile and browser-based annotations of texts, the TextAnnotator. It combines NLP methods of pre-processing with methods of flexible post-processing. Infact, machine learning (ML) requires a lot of training and test data, but is usually far from achieving perfect results. Producing high-level annotations for ML and post-correcting its results are therefore necessary. This is the purpose of TextAnnotator, which is entirely implemented in ExtJS and provides a range of interactive visualizations of annotations. In addition, it allows for flexibly integrating knowledge resources, e.g. in the course of post-processing named entity recognition. The paper describes TextAnnotator’s architecture together with three use cases: annotating temporal structures, argument structures and named entity linking.
@InProceedings{Abrami:et:al:2019, Author = {Abrami, Giuseppe and Mehler, Alexander and Lücking, Andy and Rieb, Elias and Helfrich, Philipp}, Title = {{TextAnnotator}: A flexible framework for semantic annotations}, BookTitle = {Proceedings of the Fifteenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation, (ISA-15)}, Series = {ISA-15}, location = {Gothenburg, Sweden}, month = {May}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/TextAnnotator_IWCS_Göteborg.pdf}, year = 2019, abstract ="Modern annotation tools should meet at least the following general requirements: they can handle diverse data and annotation levels within one tool, and they support the annotation process with automatic (pre-)processing outcomes as much as possible. We developed a framework that meets these general requirements and that enables versatile and browser-based annotations of texts, the TextAnnotator. It combines NLP methods of pre-processing with methods of flexible post-processing. Infact, machine learning (ML) requires a lot of training and test data, but is usually far from achieving perfect results. Producing high-level annotations for ML and post-correcting its results are therefore necessary. This is the purpose of TextAnnotator, which is entirely implemented in ExtJS and provides a range of interactive visualizations of annotations. In addition, it allows for flexibly integrating knowledge resources, e.g. in the course of post-processing named entity recognition. The paper describes TextAnnotator’s architecture together with three use cases: annotating temporal structures, argument structures and named entity linking." }
-
T. Uslu, A. Mehler, and D. Baumartz, “Computing Classifier-based Embeddings with the Help of text2ddc,” in Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing, (CICLing 2019), 2019.
[BibTeX]@inproceedings{Uslu:Mehler:Baumartz:2019, author = "Uslu, Tolga and Mehler, Alexander and Baumartz, Daniel", booktitle = "{Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing, (CICLing 2019)}", location = "La Rochelle, France", series = "{CICLing 2019}", title = "{Computing Classifier-based Embeddings with the Help of text2ddc}", year = 2019 }
-
T. Uslu, A. Mehler, C. Schulz, and D. Baumartz, “BigSense: a Word Sense Disambiguator for Big Data,” in Proceedings of the Digital Humanities 2019, (DH2019), 2019.
[BibTeX]@inproceedings{Uslu:Mehler:Schulz:Baumartz:2019, author = "Uslu, Tolga and Mehler, Alexander and Schulz, Clemens and Baumartz, Daniel", booktitle = "{Proceedings of the Digital Humanities 2019, (DH2019)}", location = "Utrecht, Netherlands", series = "{DH2019}", title = "{{BigSense}: a Word Sense Disambiguator for Big Data}", year = 2019, url={https://dev.clariah.nl/files/dh2019/boa/0199.html} }
-
W. Hemati and A. Mehler, “LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools,” Journal of Cheminformatics, vol. 11, iss. 1, p. 7, 2019.
[Abstract] [BibTeX]Chemical and biomedical named entity recognition (NER) is an essential preprocessing task in natural language processing. The identification and extraction of named entities from scientific articles is also attracting increasing interest in many scientific disciplines. Locating chemical named entities in the literature is an essential step in chemical text mining pipelines for identifying chemical mentions, their properties, and relations as discussed in the literature. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of chemical named entities. For this purpose, we transform the task of NER into a sequence labeling problem. We present a series of sequence labeling systems that we used, adapted and optimized in our experiments for solving this task. To this end, we experiment with hyperparameter optimization. Finally, we present LSTMVoter, a two-stage application of recurrent neural networks that integrates the optimized sequence labelers from our study into a single ensemble classifier.
@article{Hemati:Mehler:2019a, abstract = "Chemical and biomedical named entity recognition (NER) is an essential preprocessing task in natural language processing. The identification and extraction of named entities from scientific articles is also attracting increasing interest in many scientific disciplines. Locating chemical named entities in the literature is an essential step in chemical text mining pipelines for identifying chemical mentions, their properties, and relations as discussed in the literature. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of chemical named entities. For this purpose, we transform the task of NER into a sequence labeling problem. We present a series of sequence labeling systems that we used, adapted and optimized in our experiments for solving this task. To this end, we experiment with hyperparameter optimization. Finally, we present LSTMVoter, a two-stage application of recurrent neural networks that integrates the optimized sequence labelers from our study into a single ensemble classifier.", author = "Hemati, Wahed and Mehler, Alexander", day = "10", doi = "10.1186/s13321-018-0327-2", issn = "1758-2946", journal = "Journal of Cheminformatics", month = "Jan", number = "1", pages = "7", title = "{{LSTMVoter}: chemical named entity recognition using a conglomerate of sequence labeling tools}", url = "https://doi.org/10.1186/s13321-018-0327-2", volume = "11", year = "2019" }
-
G. Abrami, A. Mehler, and C. Spiekermann, “Graph-based Format for Modeling Multimodal Annotations in Virtual Reality by Means of VAnnotatoR,” in Proceedings of the 21th International Conference on Human-Computer Interaction, HCII 2019, Cham, 2019, pp. 351-358.
[Abstract] [BibTeX]Projects in the field of Natural Language Processing (NLP), the Digital Humanities (DH) and related disciplines dealing with machine learning of complex relationships between data objects need annotations to obtain sufficiently rich training and test sets. The visualization of such data sets and their underlying Human Computer Interaction (HCI) are perennial problems of computer science. However, despite some success stories, the clarity of information presentation and the flexibility of the annotation process may decrease with the complexity of the underlying data objects and their relationships. In order to face this problem, the so-called VAnnotatoR was developed, as a flexible annotation tool using 3D glasses and augmented reality devices, which enables annotation and visualization in three-dimensional virtual environments. In addition, multimodal objects are annotated and visualized within a graph-based approach.
@InProceedings{Abrami:Mehler:Spiekermann:2019, Author = {Abrami, Giuseppe and Mehler, Alexander and Spiekermann, Christian}, Title = {{Graph-based Format for Modeling Multimodal Annotations in Virtual Reality by Means of VAnnotatoR}}, BookTitle = {Proceedings of the 21th International Conference on Human-Computer Interaction, HCII 2019}, Series = {HCII 2019}, location = {Orlando, Florida, USA}, editor = {Stephanidis, Constantine and Antona, Margherita}, month = {July}, publisher="Springer International Publishing", address="Cham", pages="351--358", abstract="Projects in the field of Natural Language Processing (NLP), the Digital Humanities (DH) and related disciplines dealing with machine learning of complex relationships between data objects need annotations to obtain sufficiently rich training and test sets. The visualization of such data sets and their underlying Human Computer Interaction (HCI) are perennial problems of computer science. However, despite some success stories, the clarity of information presentation and the flexibility of the annotation process may decrease with the complexity of the underlying data objects and their relationships. In order to face this problem, the so-called VAnnotatoR was developed, as a flexible annotation tool using 3D glasses and augmented reality devices, which enables annotation and visualization in three-dimensional virtual environments. In addition, multimodal objects are annotated and visualized within a graph-based approach.", isbn="978-3-030-30712-7", pdf ={https://link.springer.com/content/pdf/10.1007%2F978-3-030-30712-7_44.pdf}, year = 2019 }
-
A. Mehler, T. Uslu, R. Gleim, and D. Baumartz, “text2ddc meets Literature – Ein Verfahren für die Analyse und Visualisierung thematischer Makrostrukturen,” in Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019, 2019.
[Poster][BibTeX]@InProceedings{Mehler:Uslu:Gleim:Baumartz:2019, Author = {Mehler, Alexander and Uslu, Tolga and Gleim, Rüdiger and Baumartz, Daniel}, Title = {{text2ddc meets Literature - Ein Verfahren für die Analyse und Visualisierung thematischer Makrostrukturen}}, BookTitle = {Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/DHD_Poster___text2ddc_meets_Literature_Poster.pdf}, Series = {DHd 2019}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/Preprint_DHd2019_text2ddc_meets_Literature.pdf}, location = {Frankfurt, Germany}, year = 2019 }
-
G. Abrami, C. Spiekermann, and A. Mehler, “VAnnotatoR: Ein Werkzeug zur Annotation multimodaler Netzwerke in dreidimensionalen virtuellen Umgebungen,” in Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019, 2019.
[Poster][BibTeX]@InProceedings{Abrami:Spiekermann:Mehler:2019, Author = {Abrami, Giuseppe and Spiekermann, Christian and Mehler, Alexander}, Title = {{VAnnotatoR: Ein Werkzeug zur Annotation multimodaler Netzwerke in dreidimensionalen virtuellen Umgebungen}}, BookTitle = {Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019}, Series = {DHd 2019}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/Preprint_VAnnotatoR_DHd2019.pdf}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/DHDVAnnotatoRPoster.pdf}, location = {Frankfurt, Germany}, year = 2019 }
-
W. Hemati, A. Mehler, T. Uslu, and G. Abrami, “Der TextImager als Front- und Backend für das verteilte NLP von Big Digital Humanities Data,” in Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019, 2019.
[Poster][BibTeX]@InProceedings{Hemati:Mehler:Uslu:Abrami:2019, Author = {Hemati, Wahed and Mehler, Alexander and Uslu, Tolga and Abrami, Giuseppe}, Title = {{Der TextImager als Front- und Backend für das verteilte NLP von Big Digital Humanities Data}}, BookTitle = {Proceedings of the 6th Digital Humanities Conference in the German-speaking Countries, DHd 2019}, Series = {DHd 2019}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/Der-TextImager-als-Fron-und-Backend.pdf}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/DHD19_TextImager.pdf}, location = {Frankfurt, Germany}, year = 2019 }
-
R. Gleim, S. Eger, A. Mehler, T. Uslu, W. Hemati, A. Lücking, A. Henlein, S. Kahlsdorf, and A. Hoenen, “A practitioner’s view: a survey and comparison of lemmatization and morphological tagging in German and Latin,” Journal of Language Modeling, 2019.
[BibTeX]@article{Gleim:Eger:Mehler:2019, author = {Gleim, R\"{u}diger and Eger, Steffen and Mehler, Alexander and Uslu, Tolga and Hemati, Wahed and L\"{u}cking, Andy and Henlein, Alexander and Kahlsdorf, Sven and Hoenen, Armin}, title = {A practitioner's view: a survey and comparison of lemmatization and morphological tagging in German and Latin}, journal = {Journal of Language Modeling}, year = {2019}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/07/jlm-tagging.pdf}, doi = {10.15398/jlm.v7i1.205}, url = {http://jlm.ipipan.waw.pl/index.php/JLM/article/view/205} }
2018 (37)
-
A. Hoenen, “Multi Modal Distance – An Approach to Stemma Generation With Weighting,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{HOENEN18.285, author = {Armin Hoenen}, title = "{Multi Modal Distance - An Approach to Stemma Generation With Weighting}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, url={http://www.lrec-conf.org/proceedings/lrec2018/pdf/285.pdf}, language = {english} }
-
A. Hoenen, “From Manuscripts to Archetypes through Iterative Clustering,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{HOENEN18.314, author = {Armin Hoenen}, title = "{From Manuscripts to Archetypes through Iterative Clustering}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, url={http://www.lrec-conf.org/proceedings/lrec2018/pdf/314.pdf}, language = {english} }
-
A. Hoenen and N. Schenk, “Knowing the Author by the Company His Words Keep,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{HOENEN18.349, author = {Armin Hoenen and Niko Schenk}, title = "{Knowing the Author by the Company His Words Keep}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, url={http://www.lrec-conf.org/proceedings/lrec2018/pdf/349.pdf}, language = {english} }
-
A. Hoenen, “Attempts at Visualization of Etymological Information,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, 7-12 2018.
[BibTeX]@InProceedings{HOENEN18.9, author = {Armin Hoenen}, title = {Attempts at Visualization of Etymological Information}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Kernerman, Ilan and Krek, Simon}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-28-3}, language = {english}, url={http://lrec-conf.org/workshops/lrec2018/W33/pdf/book_of_proceedings.pdf} }
-
A. Hoenen, “Tools, evaluation and preprocessing for stemmatology,” Dissertation PhD Thesis, 2018.
[BibTeX]@phdthesis{Hoenen2018, type = {Dissertation}, author = {Armin Hoenen}, title = {Tools, evaluation and preprocessing for stemmatology}, school = {Goethe University Frankfurt}, year = {2018} }
-
A. Hoenen and L. Samushia, “Principles Aiding in Reading Abbreviations in Old Georgian and Latin,” in DHd 2018, 2018.
[BibTeX]@InProceedings{Hoenen:Samushia:2018dhd, Author = {Hoenen, Armin and Samushia, Lela}, Title = {{Principles Aiding in Reading Abbreviations in Old Georgian and Latin}}, BookTitle = {DHd 2018}, url = {http://dhd2018.uni-koeln.de/wp-content/uploads/boa-DHd2018-web-ISBN.pdf}, year = 2018 }
-
A. Hoenen, “Wikipedia Mention Graphs by Example,” in EADH 2018, 2018.
[BibTeX]@InProceedings{Hoenen:2018eadh, Author = {Hoenen, Armin}, Title = {{Wikipedia Mention Graphs by Example}}, BookTitle = {EADH 2018}, url = {https://eadh2018.exordo.com/files/papers/37/final_draft/MentionGraphsEADH.pdf}, year = 2018 }
-
A. Hoenen, “Annotated Timelines and Stacked Area Plots for Visualization in Lexicography,” in Elexis workshop at EADH 2018, 2018.
[BibTeX]@InProceedings{Hoenen:2018elexis, Author = {Hoenen, Armin}, Title = {{Annotated Timelines and Stacked Area Plots for Visualization in Lexicography}}, BookTitle = {Elexis workshop at EADH 2018}, url = {https://lexdhai.insight-centre.org/Lex_DH__AI_2018_paper_2.pdf}, year = 2018 }
-
A. Hoenen, “Recurrence Analysis Function, a Dynamic Heatmap for the Visualization of Verse Text and Beyond,” in Visualisierung sprachlicher Daten: Visual Linguistics – Praxis – Tools, Heidelberg University Press, 2018.
[Abstract] [BibTeX]The Recurrence Analysis Function (ReAF) is a cross-linguistic visualization tool for (historical) verse text, especially handwritten epics. It can also provide a general visualization of various aspects of prose text. It aims to enable intuitive understanding through explorative data analysis of historical, especially bardic-oral texts.1 The assumption behind this is that bardic/born-oral and non-bardic/born-written texts differ drastically in the way they employ repetition. The ReAF in its first implementation, as presented here, is a language-independent tool that permits the visual exploration of such structures. Firstly, general aspects and formal characteristics of oral verse text are characterized, before the main technical details and some additional applications of the ReAF are explained and illustrated.
@InBook{Hoenen:2018, Author = {Hoenen, Armin}, Title = {Recurrence Analysis Function, a Dynamic Heatmap for the Visualization of Verse Text and Beyond}, BookTitle = {Visualisierung sprachlicher Daten: Visual Linguistics – Praxis – Tools}, Publisher = {Heidelberg University Press}, abstract = {The Recurrence Analysis Function (ReAF) is a cross-linguistic visualization tool for (historical) verse text, especially handwritten epics. It can also provide a general visualization of various aspects of prose text. It aims to enable intuitive understanding through explorative data analysis of historical, especially bardic-oral texts.1 The assumption behind this is that bardic/born-oral and non-bardic/born-written texts differ drastically in the way they employ repetition. The ReAF in its first implementation, as presented here, is a language-independent tool that permits the visual exploration of such structures. Firstly, general aspects and formal characteristics of oral verse text are characterized, before the main technical details and some additional applications of the ReAF are explained and illustrated. }, year = 2018, editors = {Bubenhofer, Noah and Kupietz, Marc}, place= Heidelberg, url ={https://heiup.uni-heidelberg.de/reader/download/345/345-69-80909-2-10-20180411.pdf} }
-
T. Lokot, A. Mehler, and O. Abramov, “On the limit value of compactness of some graph classes,” PLOS ONE, vol. 13, iss. 11, pp. 1-8, 2018.
[Abstract] [BibTeX]In this paper, we study the limit of compactness which is a graph index originally introduced for measuring structural characteristics of hypermedia. Applying compactness to large scale small-world graphs (Mehler, 2008) observed its limit behaviour to be equal 1. The striking question concerning this finding was whether this limit behaviour resulted from the specifics of small-world graphs or was simply an artefact. In this paper, we determine the necessary and sufficient conditions for any sequence of connected graphs resulting in a limit value of CB = 1 which can be generalized with some consideration for the case of disconnected graph classes (Theorem 3). This result can be applied to many well-known classes of connected graphs. Here, we illustrate it by considering four examples. In fact, our proof-theoretical approach allows for quickly obtaining the limit value of compactness for many graph classes sparing computational costs.
@article{Lokot:Mehler:Abramov:2018, author = {Lokot, Tatiana and Mehler, Alexander and Abramov, Olga}, journal = {PLOS ONE}, publisher = {Public Library of Science}, title = {On the limit value of compactness of some graph classes}, year = {2018}, month = {11}, volume = {13}, url = {https://doi.org/10.1371/journal.pone.0207536}, pages = {1-8}, abstract = {In this paper, we study the limit of compactness which is a graph index originally introduced for measuring structural characteristics of hypermedia. Applying compactness to large scale small-world graphs (Mehler, 2008) observed its limit behaviour to be equal 1. The striking question concerning this finding was whether this limit behaviour resulted from the specifics of small-world graphs or was simply an artefact. In this paper, we determine the necessary and sufficient conditions for any sequence of connected graphs resulting in a limit value of CB = 1 which can be generalized with some consideration for the case of disconnected graph classes (Theorem 3). This result can be applied to many well-known classes of connected graphs. Here, we illustrate it by considering four examples. In fact, our proof-theoretical approach allows for quickly obtaining the limit value of compactness for many graph classes sparing computational costs.}, number = {11}, doi = {10.1371/journal.pone.0207536} }
-
E. Rutherford, W. Hemati, and A. Mehler, “Corpus2Wiki: A MediaWiki based Annotation & Visualisation Tool for the Digital Humanities,” in INF-DH-2018, Bonn, 2018.
[BibTeX]@inproceedings{Rutherford:et:al:2018, author = {Rutherford, Eleanor AND Hemati, Wahed AND Mehler, Alexander}, title = {{Corpus2Wiki}: A MediaWiki based Annotation \& Visualisation Tool for the Digital Humanities}, booktitle = {INF-DH-2018}, year = {2018}, editor = {Burghardt, Manuel AND Müller-Birn, Claudia}, publisher = {Gesellschaft für Informatik e.V.}, address = {Bonn} }
-
G. Abrami, A. Mehler, P. Helfrich, and E. Rieb, “TextAnnotator: A Browser-based Framework for Annotating Textual Data in Digital Humanities,” in Proceedings of the Digital Humanities Austria 2018, 2018.
[BibTeX]@InProceedings{Abrami:et:al:2018, Author = {Giuseppe Abrami and Alexander Mehler and Philipp Helfrich and Elias Rieb}, Title = {{TextAnnotator}: A Browser-based Framework for Annotating Textual Data in Digital Humanities}, BookTitle = {Proceedings of the Digital Humanities Austria 2018}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/04/TA__A_Browser_based_Framework_for_Annotating_Textual_Data_in_Digital_Humanities.pdf}, location = {Salzburg, Austria}, year = 2018 }
-
S. Ahmed and A. Mehler, “Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large Corpora,” in Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018.
[Abstract] [BibTeX]This study improves the performance of neural named entity recognition by a margin of up to 11% in terms of F-score on the example of a low-resource language like German, thereby outperforming existing baselines and establishing a new state-of-the-art on each single open-source dataset (CoNLL 2003, GermEval 2014 and Tübingen Treebank 2018). Rather than designing deeper and wider hybrid neural architectures, we gather all available resources and perform a detailed optimization and grammar-dependent morphological processing consisting of lemmatization and part-of-speech tagging prior to exposing the raw data to any training process. We test our approach in a threefold monolingual experimental setup of a) single, b) joint, and c) optimized training and shed light on the dependency of downstream-tasks on the size of corpora used to compute word embeddings.
@InProceedings{Ahmed:Mehler:2018, author = {Sajawel Ahmed and Alexander Mehler}, title = {{Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large Corpora}}, abstract = {This study improves the performance of neural named entity recognition by a margin of up to 11% in terms of F-score on the example of a low-resource language like German, thereby outperforming existing baselines and establishing a new state-of-the-art on each single open-source dataset (CoNLL 2003, GermEval 2014 and Tübingen Treebank 2018). Rather than designing deeper and wider hybrid neural architectures, we gather all available resources and perform a detailed optimization and grammar-dependent morphological processing consisting of lemmatization and part-of-speech tagging prior to exposing the raw data to any training process. We test our approach in a threefold monolingual experimental setup of a) single, b) joint, and c) optimized training and shed light on the dependency of downstream-tasks on the size of corpora used to compute word embeddings.}, booktitle = {Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA)}, location = {Orlando, Florida, USA}, pdf = {https://arxiv.org/pdf/1807.10675.pdf}, year = 2018 }
-
C. Weiland, C. Driller, M. Koch, M. Schmidt, G. Abrami, S. Ahmed, A. Mehler, A. Pachzelt, G. Kasperek, A. Hausinger, and T. Hörnschemeyer, “BioFID, a platform to enhance accessibility of biodiversity data,” in Proceedings of the 10th International Conference on Ecological Informatics, 2018.
[BibTeX]@inproceedings{Weiland:et:al:2018, author = {Claus Weiland and Christine Driller and Markus Koch and Marco Schmidt and Giuseppe Abrami and Sajawel Ahmed and Alexander Mehler and Adrian Pachzelt and Gerwin Kasperek and Angela Hausinger and Thomas Hörnschemeyer}, title = {{BioFID}, a platform to enhance accessibility of biodiversity data}, BookTitle = {Proceedings of the 10th International Conference on Ecological Informatics}, year = {2018}, url={https://www.researchgate.net/profile/Marco_Schmidt3/publication/327940813_BIOfid_a_Platform_to_Enhance_Accessibility_of_Biodiversity_Data/links/5bae3e3e92851ca9ed2cd60f/BIOfid-a-Platform-to-Enhance-Accessibility-of-Biodiversity-Data.pdf?origin=publication_detail}, location = {Jena, Germany} }
-
A. Kett, G. Abrami, A. Mehler, and C. Spiekermann, “Resources2City Explorer: A System for Generating Interactive Walkable Virtual Cities out of File Systems,” in Proceedings of the 31st ACM User Interface Software and Technology Symposium, 2018.
[Abstract] [Poster][BibTeX]We present Resources2City Explorer (R2CE), a tool for representing file systems as interactive, walkable virtual cities. R2CE visualizes file systems based on concepts of spatial, 3D information processing. For this purpose, it extends the range of functions of conventional file browsers considerably. Visual elements in a city generated by R2CE represent (relations of) objects of the underlying file system. The paper describes the functional spectrum of R2CE and illustrates it by visualizing a sample of 940 files.
@InProceedings{Kett:et:al:2018, Author = {Attila Kett and Giuseppe Abrami and Alexander Mehler and Christian Spiekermann}, Title = {{Resources2City Explorer}: A System for Generating Interactive Walkable Virtual Cities out of File Systems}, BookTitle = {Proceedings of the 31st ACM User Interface Software and Technology Symposium}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2018/10/UIST2018Final.pdf}, location = {Berlin, Germany}, abstract = {We present Resources2City Explorer (R2CE), a tool for representing file systems as interactive, walkable virtual cities. R2CE visualizes file systems based on concepts of spatial, 3D information processing. For this purpose, it extends the range of functions of conventional file browsers considerably. Visual elements in a city generated by R2CE represent (relations of) objects of the underlying file system. The paper describes the functional spectrum of R2CE and illustrates it by visualizing a sample of 940 files.}, year = 2018 }
-
A. Lücking, “Witness-loaded and Witness-free Demonstratives,” in Atypical Demonstratives, M. Coniglio, A. Murphy, E. Schlachter, and T. Veenstra, Eds., De Gruyter, 2018.
[BibTeX]@InCollection{Luecking:2018:a, author = {Andy L\"{u}cking}, title = {Witness-loaded and Witness-free Demonstratives}, booktitle = {Atypical Demonstratives}, publisher = {De Gruyter}, year = 2018, editor = {Marco Coniglio and Andrew Murphy and Eva Schlachter and Tonjes Veenstra}, isbn = {978-3-11-056029-9}, url={https://www.degruyter.com/view/product/495228}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2020/05/Luecking-witness-loading-rg.pdf} }
-
A. Lücking and J. Ginzburg, “`Most people but not Bill’: integrating sets, individuals and negation into a cognitively plausible account of noun phrase interpretation,” in Proceedings of Cognitive Structures: Linguistic, Philosophical and Psychological Perspectives, 2018.
[BibTeX]@InProceedings{Luecking:Ginzburg:2018, title = {`Most people but not {Bill}': integrating sets, individuals and negation into a cognitively plausible account of noun phrase interpretation}, booktitle = {Proceedings of Cognitive Structures: Linguistic, Philosophical and Psychological Perspectives}, series = {CoSt'18}, author = {L\"{u}cking, Andy and Ginzburg, Jonathan}, year = 2018 }
-
T. Uslu and A. Mehler, “PolyViz: a Visualization System for a Special Kind of Multipartite Graphs,” in Proceedings of the IEEE VIS 2018, 2018.
[BibTeX]@InProceedings{Uslu:Mehler:2018, Author = {Tolga Uslu and Alexander Mehler}, Title = {{PolyViz}: a Visualization System for a Special Kind of Multipartite Graphs}, BookTitle = {Proceedings of the IEEE VIS 2018}, Series = {IEEE VIS 2018}, location = {Berlin, Germany}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/07/polyviz-visualization-system.pdf}, year = 2018 }
-
D. Baumartz, T. Uslu, and A. Mehler, “LTV: Labeled Topic Vector,” in Proceedings of COLING 2018, the 27th International Conference on Computational Linguistics: System Demonstrations, August 20-26, Santa Fe, New Mexico, USA, 2018.
[Abstract] [BibTeX]In this paper, we present LTV, a website and an API that generate labeled topic classifications based on the Dewey Decimal Classification (DDC), an international standard for topic classification in libraries. We introduce nnDDC, a largely language-independent neural network-based classifier for DDC-related topic classification, which we optimized using a wide range of linguistic features to achieve an F-score of 87.4%. To show that our approach is language-independent, we evaluate nnDDC using up to 40 different languages. We derive a topic model based on nnDDC, which generates probability distributions over semantic units for any input on sense-, word- and text-level. Unlike related approaches, however, these probabilities are estimated by means of nnDDC so that each dimension of the resulting vector representation is uniquely labeled by a DDC class. In this way, we introduce a neural network-based Classifier-Induced Semantic Space (nnCISS).
@InProceedings{Baumartz:Uslu:Mehler:2018, author = {Daniel Baumartz and Tolga Uslu and Alexander Mehler}, title = {{LTV}: Labeled Topic Vector}, booktitle = {Proceedings of {COLING 2018}, the 27th International Conference on Computational Linguistics: System Demonstrations, August 20-26}, year = {2018}, address = {Santa Fe, New Mexico, USA}, publisher = {The COLING 2018 Organizing Committee}, abstract = {In this paper, we present LTV, a website and an API that generate labeled topic classifications based on the Dewey Decimal Classification (DDC), an international standard for topic classification in libraries. We introduce nnDDC, a largely language-independent neural network-based classifier for DDC-related topic classification, which we optimized using a wide range of linguistic features to achieve an F-score of 87.4%. To show that our approach is language-independent, we evaluate nnDDC using up to 40 different languages. We derive a topic model based on nnDDC, which generates probability distributions over semantic units for any input on sense-, word- and text-level. Unlike related approaches, however, these probabilities are estimated by means of nnDDC so that each dimension of the resulting vector representation is uniquely labeled by a DDC class. In this way, we introduce a neural network-based Classifier-Induced Semantic Space (nnCISS).}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/06/coling2018.pdf} }
-
C. Driller, M. Koch, M. Schmidt, C. Weiland, T. Hörnschemeyer, T. Hickler, G. Abrami, S. Ahmed, R. Gleim, W. Hemati, T. Uslu, A. Mehler, A. Pachzelt, J. Rexhepi, T. Risse, J. Schuster, G. Kasperek, and A. Hausinger, “Workflow and Current Achievements of BIOfid, an Information Service Mobilizing Biodiversity Data from Literature Sources,” Biodiversity Information Science and Standards, vol. 2, p. e25876, 2018.
[Abstract] [BibTeX]BIOfid is a specialized information service currently being developed to mobilize biodiversity data dormant in printed historical and modern literature and to offer a platform for open access journals on the science of biodiversity. Our team of librarians, computer scientists and biologists produce high-quality text digitizations, develop new text-mining tools and generate detailed ontologies enabling semantic text analysis and semantic search by means of user-specific queries. In a pilot project we focus on German publications on the distribution and ecology of vascular plants, birds, moths and butterflies extending back to the Linnaeus period about 250 years ago. The three organism groups have been selected according to current demands of the relevant research community in Germany. The text corpus defined for this purpose comprises over 400 volumes with more than 100,000 pages to be digitized and will be complemented by journals from other digitization projects, copyright-free and project-related literature. With TextImager (Natural Language Processing & Text Visualization) and TextAnnotator (Discourse Semantic Annotation) we have already extended and launched tools that focus on the text-analytical section of our project. Furthermore, taxonomic and anatomical ontologies elaborated by us for the taxa prioritized by the project’s target group - German institutions and scientists active in biodiversity research - are constantly improved and expanded to maximize scientific data output. Our poster describes the general workflow of our project ranging from literature acquisition via software development, to data availability on the BIOfid web portal (http://biofid.de/), and the implementation into existing platforms which serve to promote global accessibility of biodiversity data.
@article{Driller:et:al:2018, author = {Christine Driller and Markus Koch and Marco Schmidt and Claus Weiland and Thomas Hörnschemeyer and Thomas Hickler and Giuseppe Abrami and Sajawel Ahmed and Rüdiger Gleim and Wahed Hemati and Tolga Uslu and Alexander Mehler and Adrian Pachzelt and Jashar Rexhepi and Thomas Risse and Janina Schuster and Gerwin Kasperek and Angela Hausinger}, title = {Workflow and Current Achievements of BIOfid, an Information Service Mobilizing Biodiversity Data from Literature Sources}, volume = {2}, number = {}, year = {2018}, doi = {10.3897/biss.2.25876}, publisher = {Pensoft Publishers}, abstract = {BIOfid is a specialized information service currently being developed to mobilize biodiversity data dormant in printed historical and modern literature and to offer a platform for open access journals on the science of biodiversity. Our team of librarians, computer scientists and biologists produce high-quality text digitizations, develop new text-mining tools and generate detailed ontologies enabling semantic text analysis and semantic search by means of user-specific queries. In a pilot project we focus on German publications on the distribution and ecology of vascular plants, birds, moths and butterflies extending back to the Linnaeus period about 250 years ago. The three organism groups have been selected according to current demands of the relevant research community in Germany. The text corpus defined for this purpose comprises over 400 volumes with more than 100,000 pages to be digitized and will be complemented by journals from other digitization projects, copyright-free and project-related literature. With TextImager (Natural Language Processing & Text Visualization) and TextAnnotator (Discourse Semantic Annotation) we have already extended and launched tools that focus on the text-analytical section of our project. Furthermore, taxonomic and anatomical ontologies elaborated by us for the taxa prioritized by the project’s target group - German institutions and scientists active in biodiversity research - are constantly improved and expanded to maximize scientific data output. Our poster describes the general workflow of our project ranging from literature acquisition via software development, to data availability on the BIOfid web portal (http://biofid.de/), and the implementation into existing platforms which serve to promote global accessibility of biodiversity data.}, issn = {}, pages = {e25876}, URL = {https://doi.org/10.3897/biss.2.25876}, eprint = {https://doi.org/10.3897/biss.2.25876}, journal = {Biodiversity Information Science and Standards} }
-
A. Mehler, G. Abrami, C. Spiekermann, and M. Jostock, “VAnnotatoR: A Framework for Generating Multimodal Hypertexts,” in Proceedings of the 29th ACM Conference on Hypertext and Social Media, New York, NY, USA, 2018.
[BibTeX]@InProceedings{Mehler:Abrami:Spiekermann:Jostock:2018, author = {Mehler, Alexander and Abrami, Giuseppe and Spiekermann, Christian and Jostock, Matthias}, title = {{VAnnotatoR}: {A} Framework for Generating Multimodal Hypertexts}, booktitle = {Proceedings of the 29th ACM Conference on Hypertext and Social Media}, series = {Proceedings of the 29th ACM Conference on Hypertext and Social Media (HT '18)}, year = {2018}, location = {Baltimore, Maryland}, publisher = {ACM}, address = {New York, NY, USA}, pdf = {http://delivery.acm.org/10.1145/3210000/3209572/p150-mehler.pdf} }
-
W. Hemati, A. Mehler, T. Uslu, D. Baumartz, and G. Abrami, “Evaluating and Integrating Databases in the Area of NLP,” in International Quantitative Linguistics Conference (QUALICO 2018), 2018.
[Poster][BibTeX]@inproceedings{Hemati:Mehler:Uslu:Baumartz:Abrami:2018, author={Wahed Hemati and Alexander Mehler and Tolga Uslu and Daniel Baumartz and Giuseppe Abrami}, title={Evaluating and Integrating Databases in the Area of {NLP}}, booktitle={International Quantitative Linguistics Conference (QUALICO 2018)}, year={2018}, pdf={https://www.texttechnologylab.org/wp-content/uploads/2018/04/Hemat-Mehler-Uslu-Baumartz-Abrami-Qualico-2018.pdf}, poster={https://www.texttechnologylab.org/wp-content/uploads/2018/10/qualico2018_databases_poster_hemati_mehler_uslu_baumartz_abrami.pdf}, location={Wroclaw, Poland} }
-
G. Abrami, G. Boden, and L. Gleiß, “World of the Khwe Bushmen: Accessing Khwe Cultural Heritage data by means of a digital ontology based on OWLnotator,” in Proceedings of the Digital Humanities 2018, 2018.
[BibTeX]@InProceedings{Abrami:Boden:Gleiss:2018, Author = {Abrami, Giuseppe and Boden, Gertrud and Glei\ss{}, Lisa}, Title = {{World of the Khwe Bushmen: Accessing Khwe Cultural Heritage data by means of a digital ontology based on OWLnotator}}, BookTitle = {Proceedings of the Digital Humanities 2018}, Series = {DH2018}, location = {Mexico City, Mexico}, year = 2018 }
-
A. Mehler, W. Hemati, R. Gleim, and D. Baumartz, “VienNA: Auf dem Weg zu einer Infrastruktur für die verteilte interaktive evolutionäre Verarbeitung natürlicher Sprache,” in Forschungsinfrastrukturen und digitale Informationssysteme in der germanistischen Sprachwissenschaft , H. Lobin, R. Schneider, and A. Witt, Eds., Berlin: De Gruyter, 2018, vol. 6.
[BibTeX]@InCollection{Mehler:Hemati:Gleim:Baumartz:2018, Author = {Alexander Mehler and Wahed Hemati and Rüdiger Gleim and Daniel Baumartz}, Title = {{VienNA: }{Auf dem Weg zu einer Infrastruktur für die verteilte interaktive evolutionäre Verarbeitung natürlicher Sprache}}, BookTitle = {Forschungsinfrastrukturen und digitale Informationssysteme in der germanistischen Sprachwissenschaft }, Publisher = {De Gruyter}, Editor = {Henning Lobin and Roman Schneider and Andreas Witt}, Volume = {6}, Address = {Berlin}, year = 2018 }
-
A. Mehler, W. Hemati, T. Uslu, and A. Lücking, “A Multidimensional Model of Syntactic Dependency Trees for Authorship Attribution,” in Quantitative analysis of dependency structures, J. Jiang and H. Liu, Eds., Berlin/New York: De Gruyter, 2018.
[Abstract] [BibTeX]Abstract: In this chapter we introduce a multidimensional model of syntactic dependency trees. Our ultimate goal is to generate fingerprints of such trees to predict the author of the underlying sentences. The chapter makes a first attempt to create such fingerprints for sentence categorization via the detour of text categorization. We show that at text level, aggregated dependency structures actually provide information about authorship. At the same time, we show that this does not hold for topic detection. We evaluate our model using a quarter of a million sentences collected in two corpora: the first is sampled from literary texts, the second from Wikipedia articles. As a second finding of our approach, we show that quantitative models of dependency structure do not yet allow for detecting syntactic alignment in written communication. We conclude that this is mainly due to effects of lexical alignment on syntactic alignment.
@InCollection{Mehler:Hemati:Uslu:Luecking:2018, Author = {Alexander Mehler and Wahed Hemati and Tolga Uslu and Andy Lücking}, Title = {A Multidimensional Model of Syntactic Dependency Trees for Authorship Attribution}, BookTitle = {Quantitative analysis of dependency structures}, Publisher = {De Gruyter}, Editor = {Jingyang Jiang and Haitao Liu}, Address = {Berlin/New York}, abstract = {Abstract: In this chapter we introduce a multidimensional model of syntactic dependency trees. Our ultimate goal is to generate fingerprints of such trees to predict the author of the underlying sentences. The chapter makes a first attempt to create such fingerprints for sentence categorization via the detour of text categorization. We show that at text level, aggregated dependency structures actually provide information about authorship. At the same time, we show that this does not hold for topic detection. We evaluate our model using a quarter of a million sentences collected in two corpora: the first is sampled from literary texts, the second from Wikipedia articles. As a second finding of our approach, we show that quantitative models of dependency structure do not yet allow for detecting syntactic alignment in written communication. We conclude that this is mainly due to effects of lexical alignment on syntactic alignment.}, keywords = {Dependency structure, Authorship attribution, Text categorization, Syntactic Alignment}, year = 2018 }
-
T. Uslu, A. Mehler, and D. Meyer, “LitViz: Visualizing Literary Data by Means of text2voronoi,” in Proceedings of the Digital Humanities 2018, 2018.
[BibTeX]@InProceedings{Uslu:Mehler:Meyer:2018, Author = {Tolga Uslu and Alexander Mehler and Dirk Meyer}, Title = {{{LitViz}: Visualizing Literary Data by Means of text2voronoi}}, BookTitle = {Proceedings of the Digital Humanities 2018}, Series = {DH2018}, location = {Mexico City, Mexico}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/LitViz.pdf}, year = 2018 }
-
C. Spiekermann, G. Abrami, and A. Mehler, “VAnnotatoR: a Gesture-driven Annotation Framework for Linguistic and Multimodal Annotation,” in Proceedings of the Annotation, Recognition and Evaluation of Actions (AREA 2018) Workshop, 2018.
[BibTeX]@InProceedings{Spiekerman:Abrami:Mehler:2018, Author = {Christian Spiekermann and Giuseppe Abrami and Alexander Mehler}, Title = {{VAnnotatoR}: a Gesture-driven Annotation Framework for Linguistic and Multimodal Annotation}, BookTitle = {Proceedings of the Annotation, Recognition and Evaluation of Actions (AREA 2018) Workshop}, Series = {AREA}, location = {Miyazaki, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/VAnnotatoR.pdf}, year = 2018 }
-
T. Uslu, L. Miebach, S. Wolfsgruber, M. Wagner, K. Fließbach, R. Gleim, W. Hemati, A. Henlein, and A. Mehler, “Automatic Classification in Memory Clinic Patients and in Depressive Patients,” in Proceedings of Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric impairments (RaPID-2), 2018.
[BibTeX]@InProceedings{Uslu:et:al:2018:a, Author = {Tolga Uslu and Lisa Miebach and Steffen Wolfsgruber and Michael Wagner and Klaus Fließbach and Rüdiger Gleim and Wahed Hemati and Alexander Henlein and Alexander Mehler}, Title = {{Automatic Classification in Memory Clinic Patients and in Depressive Patients}}, BookTitle = {Proceedings of Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric impairments (RaPID-2)}, Series = {RaPID}, location = {Miyazaki, Japan}, year = 2018 }
-
A. Mehler, R. Gleim, A. Lücking, T. Uslu, and C. Stegbauer, “On the Self-similarity of Wikipedia Talks: a Combined Discourse-analytical and Quantitative Approach,” Glottometrics, vol. 40, pp. 1-44, 2018.
[BibTeX]@Article{Mehler:Gleim:Luecking:Uslu:Stegbauer:2018, Author = {Alexander Mehler and Rüdiger Gleim and Andy Lücking and Tolga Uslu and Christian Stegbauer}, Title = {On the Self-similarity of {Wikipedia} Talks: a Combined Discourse-analytical and Quantitative Approach}, Journal = {Glottometrics}, Volume = {40}, Pages = {1-44}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/Glottometrics-Mehler.pdf}, year = 2018 }
-
T. Uslu, A. Mehler, A. Niekler, and D. Baumartz, “Towards a DDC-based Topic Network Model of Wikipedia,” in Proceedings of 2nd International Workshop on Modeling, Analysis, and Management of Social Networks and their Applications (SOCNET 2018), February 28, 2018, 2018.
[BibTeX]@InProceedings{Uslu:Mehler:Niekler:Baumartz:2018, Author = {Tolga Uslu and Alexander Mehler and Andreas Niekler and Daniel Baumartz}, Title = {Towards a {DDC}-based Topic Network Model of Wikipedia}, BookTitle = {Proceedings of 2nd International Workshop on Modeling, Analysis, and Management of Social Networks and their Applications (SOCNET 2018), February 28, 2018}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TowardsDDC.pdf}, year = 2018 }
-
T. Uslu, A. Mehler, D. Baumartz, A. Henlein, and W. Hemati, “fastSense: An Efficient Word Sense Disambiguation Classifier,” in Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 – 12, Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{Uslu:et:al:2018, Author = {Tolga Uslu and Alexander Mehler and Daniel Baumartz and Alexander Henlein and Wahed Hemati }, Title = {fastSense: An Efficient Word Sense Disambiguation Classifier}, BookTitle = {Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 - 12}, Series = {LREC 2018}, Address = {Miyazaki, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/fastSense.pdf}, year = 2018 }
-
R. Gleim, A. Mehler, and S. Y. Song, “WikiDragon: A Java Framework For Diachronic Content And Network Analysis Of MediaWikis,” in Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 – 12, Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{Gleim:Mehler:Song:2018, Author = {R{\"u}diger Gleim and Alexander Mehler and Sung Y. Song}, Title = {WikiDragon: A Java Framework For Diachronic Content And Network Analysis Of MediaWikis}, BookTitle = {Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 - 12}, Series = {LREC 2018}, Address = {Miyazaki, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/WikiDragon.pdf}, year = 2018 }
-
P. Helfrich, E. Rieb, G. Abrami, A. Lücking, and A. Mehler, “TreeAnnotator: Versatile Visual Annotation of Hierarchical Text Relations,” in Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 – 12, Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{Helfrich:et:al:2018, Author = {Philipp Helfrich and Elias Rieb and Giuseppe Abrami and Andy L{\"u}cking and Alexander Mehler}, Title = {TreeAnnotator: Versatile Visual Annotation of Hierarchical Text Relations}, BookTitle = {Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 - 12}, Series = {LREC 2018}, Address = {Miyazaki, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TreeAnnotator.pdf}, year = 2018 }
-
G. Abrami and A. Mehler, “A UIMA Database Interface for Managing NLP-related Text Annotations,” in Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 – 12, Miyazaki, Japan, 2018.
[BibTeX]@InProceedings{Abrami:Mehler:2018, Author = {Giuseppe Abrami and Alexander Mehler}, Title = {A UIMA Database Interface for Managing NLP-related Text Annotations}, BookTitle = {Proceedings of the 11th edition of the Language Resources and Evaluation Conference, May 7 - 12}, Series = {LREC 2018}, Address = {Miyazaki, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/UIMA-DI.pdf}, year = 2018 }
-
A. Mehler, C. Stegbauer, and B. Frank-Job, “Ferdinand de Saussure. 1916. Cours de linguistique générale. Payot, Lausanne/Paris,” in Schlüsselwerke der Netzwerkforschung, C. Stegbauer and B. Holzer, Eds., Wiesbaden: Springer VS, 2018.
[BibTeX]@InBook{Mehler:Stegbauer:Frank-Job:2018, Author = {Alexander Mehler and Christian Stegbauer and Barbara Frank-Job}, Editor = {Christian Stegbauer and Boris Holzer}, Title = {{Ferdinand de Saussure. 1916. Cours de linguistique générale. Payot, Lausanne/Paris}}, Publisher = {Springer VS}, Address = {Wiesbaden}, booktitle = {Schlüsselwerke der Netzwerkforschung}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2017/11/Saussure2.pdf}, year = 2018 }
-
A. Mehler, O. Zlatkin-Troitschanskaia, W. Hemati, D. Molerov, A. Lücking, and S. Schmidt, “Integrating Computational Linguistic Analysis of Multilingual Learning Data and Educational Measurement Approaches to Explore Learning in Higher Education,” in Positive Learning in the Age of Information: A Blessing or a Curse?, O. Zlatkin-Troitschanskaia, G. Wittum, and A. Dengel, Eds., Wiesbaden: Springer Fachmedien Wiesbaden, 2018, pp. 145-193.
[Abstract] [BibTeX]This chapter develops a computational linguistic model for analyzing and comparing multilingual data as well as its application to a large body of standardized assessment data from higher education. The approach employs both an automatic and a manual annotation of the data on several linguistic layers (including parts of speech, text structure and content). Quantitative features of the textual data are explored that are related to both the students' (domain-specific knowledge) test results and their level of academic experience. The respective analysis involves statistics of distance correlation, text categorization with respect to text types (questions and response options) as well as languages (English and German), and network analysis to assess dependencies between features. The correlation between correct test results of students and linguistic features of the verbal presentations of tests indicate to what extent language influences higher education test performance. It has also been found that this influence relates to specialized language. Thus, this integrative modeling approach contributes a test basis for a large-scale analysis of learning data and points to a number of subsequent, more detailed research questions.
@inbook{Mehler:et:al:2018, abstract = "This chapter develops a computational linguistic model for analyzing and comparing multilingual data as well as its application to a large body of standardized assessment data from higher education. The approach employs both an automatic and a manual annotation of the data on several linguistic layers (including parts of speech, text structure and content). Quantitative features of the textual data are explored that are related to both the students' (domain-specific knowledge) test results and their level of academic experience. The respective analysis involves statistics of distance correlation, text categorization with respect to text types (questions and response options) as well as languages (English and German), and network analysis to assess dependencies between features. The correlation between correct test results of students and linguistic features of the verbal presentations of tests indicate to what extent language influences higher education test performance. It has also been found that this influence relates to specialized language. Thus, this integrative modeling approach contributes a test basis for a large-scale analysis of learning data and points to a number of subsequent, more detailed research questions.", address = "Wiesbaden", author = "Mehler, Alexander and Zlatkin-Troitschanskaia, Olga and Hemati, Wahed and Molerov, Dimitri and L{\"u}cking, Andy and Schmidt, Susanne", booktitle = "Positive Learning in the Age of Information: A Blessing or a Curse?", doi = "10.1007/978-3-658-19567-0_10", editor = "Zlatkin-Troitschanskaia, Olga and Wittum, Gabriel and Dengel, Andreas", isbn = "978-3-658-19567-0", pages = "145--193", publisher = "Springer Fachmedien Wiesbaden", title = "Integrating Computational Linguistic Analysis of Multilingual Learning Data and Educational Measurement Approaches to Explore Learning in Higher Education", url = "https://doi.org/10.1007/978-3-658-19567-0_10", year = "2018" }
-
G. Abrami, S. Ahmed, R. Gleim, W. Hemati, A. Mehler, and U. Tolga, Natural Language Processing and Text Mining for BIOfid, 2018.
[BibTeX]@misc{Abrami:et:al:2018b, author = {Abrami, Giuseppe and Ahmed, Sajawel and Gleim, R{\"u}diger and Hemati, Wahed and Mehler, Alexander and Uslu Tolga}, title = {{Natural Language Processing and Text Mining for BIOfid}}, howpublished = {Presentation at the 1st Meeting of the Scientific Advisory Board of the BIOfid Project}, adress = {Goethe-University, Frankfurt am Main, Germany}, year = {2018}, month = {March}, day = {08}, pdf = {} }
2017 (10)
-
A. Mehler and A. Lücking, “Modelle sozialer Netzwerke und Natural Language Processing: eine methodologische Randnotiz,” Soziologie, vol. 46, iss. 1, pp. 43-47, 2017.
[BibTeX]@Article{Mehler:Luecking:2017, Author = {Alexander Mehler and Andy Lücking}, Title = {Modelle sozialer Netzwerke und Natural Language Processing: eine methodologische Randnotiz}, Journal = {Soziologie}, Volume = {46}, Number = {1}, Pages = {43-47}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/Soziologe-NetzwerkeundNLP.pdf}, year = 2017 }
-
W. Hemati, A. Mehler, and T. Uslu, “CRFVoter: Chemical Entity Mention, Gene and Protein Related Object recognition using a conglomerate of CRF based tools,” in BioCreative V.5. Proceedings, 2017.
[BibTeX]@InProceedings{Hemati:Mehler:Uslu:2017, Author = {Wahed Hemati and Alexander Mehler and Tolga Uslu}, Title = {{CRFVoter}: Chemical Entity Mention, Gene and Protein Related Object recognition using a conglomerate of CRF based tools}, BookTitle = {BioCreative V.5. Proceedings}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/CRFVoter.pdf}, year = 2017 }
-
W. Hemati, T. Uslu, and A. Mehler, “TextImager as an interface to BeCalm,” in BioCreative V.5. Proceedings, 2017.
[BibTeX]@InProceedings{Hemati:Uslu:Mehler:2017, Author = {Wahed Hemati and Tolga Uslu and Alexander Mehler}, Title = {{TextImager} as an interface to {BeCalm}}, BookTitle = {BioCreative V.5. Proceedings}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager_BeCalm.pdf}, year = 2017 }
-
A. Mehler, G. Abrami, S. Bruendel, L. Felder, T. Ostertag, and C. Spiekermann, “Stolperwege: An App for a Digital Public History of the Holocaust,” in Proceedings of the 28th ACM Conference on Hypertext and Social Media, New York, NY, USA, 2017, pp. 319-320.
[Abstract] [Poster][BibTeX]We present the Stolperwege app, a web-based framework for ubiquitous modeling of historical processes. Starting from the art project Stolpersteine of Gunter Demnig, it allows for virtually connecting these stumbling blocks with information about the biographies of victims of Nazism. According to the practice of public history, the aim of Stolperwege is to deepen public knowledge of the Holocaust in the context of our everyday environment. Stolperwege uses an information model that allows for modeling social networks of agents starting from information about portions of their life. The paper exemplifies how Stolperwege is informationally enriched by means of historical maps and 3D animations of (historical) buildings.
@InProceedings{Mehler:et:al:2017:a, Author = {Alexander Mehler and Giuseppe Abrami and Steffen Bruendel and Lisa Felder and Thomas Ostertag and Christian Spiekermann}, Title = {{Stolperwege:} An App for a Digital Public History of the {Holocaust}}, BookTitle = {Proceedings of the 28th ACM Conference on Hypertext and Social Media}, Series = {HT '17}, Pages = {319--320}, Address = {New York, NY, USA}, Publisher = {ACM}, abstract = {We present the Stolperwege app, a web-based framework for ubiquitous modeling of historical processes. Starting from the art project Stolpersteine of Gunter Demnig, it allows for virtually connecting these stumbling blocks with information about the biographies of victims of Nazism. According to the practice of public history, the aim of Stolperwege is to deepen public knowledge of the Holocaust in the context of our everyday environment. Stolperwege uses an information model that allows for modeling social networks of agents starting from information about portions of their life. The paper exemplifies how Stolperwege is informationally enriched by means of historical maps and 3D animations of (historical) buildings.}, acmid = {3078748}, doi = {10.1145/3078714.3078748}, isbn = {978-1-4503-4708-2}, keywords = {3d, geocaching, geotagging, historical maps, historical processes, public history of the holocaust, ubiquitous computing}, location = {Prague, Czech Republic}, numpages = {2}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2017/07/poster_ht2017.pdf}, url = {http://doi.acm.org/10.1145/3078714.3078748}, year = 2017 }
-
A. Mehler, R. Gleim, W. Hemati, and T. Uslu, “Skalenfreie online soziale Lexika am Beispiel von Wiktionary,” in Proceedings of 53rd Annual Conference of the Institut für Deutsche Sprache (IDS), March 14-16, Mannheim, Germany, Berlin, 2017. In German. Title translates into: Scale-free online-social Lexika by Example of Wiktionary
[Abstract] [BibTeX]In English: The paper deals with characteristics of the structural, thematic and participatory dynamics of collaboratively generated lexical networks. This is done by example of Wiktionary. Starting from a network-theoretical model in terms of so-called multi-layer networks, we describe Wiktionary as a scale-free lexicon. Systems of this sort are characterized by the fact that their content-related dynamics is determined by the underlying dynamics of collaborating authors. This happens in a way that social structure imprints on content structure. According to this conception, the unequal distribution of the activities of authors results in a correspondingly unequal distribution of the information units documented within the lexicon. The paper focuses on foundations for describing such systems starting from a parameter space which requires to deal with Wiktionary as an issue in big data analysis. In German: Der Beitrag thematisiert Eigenschaften der strukturellen, thematischen und partizipativen Dynamik kollaborativ erzeugter lexikalischer Netzwerke am Beispiel von Wiktionary. Ausgehend von einem netzwerktheoretischen Modell in Form so genannter Mehrebenennetzwerke wird Wiktionary als ein skalenfreies Lexikon beschrieben. Systeme dieser Art zeichnen sich dadurch aus, dass ihre inhaltliche Dynamik durch die zugrundeliegende Kollaborationsdynamik bestimmt wird, und zwar so, dass sich die soziale Struktur der entsprechenden inhaltlichen Struktur aufprägt. Dieser Auffassung gemäß führt die Ungleichverteilung der Aktivitäten von Lexikonproduzenten zu einer analogen Ungleichverteilung der im Lexikon dokumentierten Informationseinheiten. Der Beitrag thematisiert Grundlagen zur Beschreibung solcher Systeme ausgehend von einem Parameterraum, welcher die netzwerkanalytische Betrachtung von Wiktionary als Big-Data-Problem darstellt.
@InProceedings{Mehler:Gleim:Hemati:Uslu:2017, Author = {Alexander Mehler and Rüdiger Gleim and Wahed Hemati and Tolga Uslu}, Title = {{Skalenfreie online soziale Lexika am Beispiel von Wiktionary}}, BookTitle = {Proceedings of 53rd Annual Conference of the Institut für Deutsche Sprache (IDS), March 14-16, Mannheim, Germany}, Editor = {Stefan Engelberg and Henning Lobin and Kathrin Steyer and Sascha Wolfer}, Address = {Berlin}, Publisher = {De Gruyter}, Note = {In German. Title translates into: Scale-free online-social Lexika by Example of Wiktionary}, abstract = {In English: The paper deals with characteristics of the structural, thematic and participatory dynamics of collaboratively generated lexical networks. This is done by example of Wiktionary. Starting from a network-theoretical model in terms of so-called multi-layer networks, we describe Wiktionary as a scale-free lexicon. Systems of this sort are characterized by the fact that their content-related dynamics is determined by the underlying dynamics of collaborating authors. This happens in a way that social structure imprints on content structure. According to this conception, the unequal distribution of the activities of authors results in a correspondingly unequal distribution of the information units documented within the lexicon. The paper focuses on foundations for describing such systems starting from a parameter space which requires to deal with Wiktionary as an issue in big data analysis. In German: Der Beitrag thematisiert Eigenschaften der strukturellen, thematischen und partizipativen Dynamik kollaborativ erzeugter lexikalischer Netzwerke am Beispiel von Wiktionary. Ausgehend von einem netzwerktheoretischen Modell in Form so genannter Mehrebenennetzwerke wird Wiktionary als ein skalenfreies Lexikon beschrieben. Systeme dieser Art zeichnen sich dadurch aus, dass ihre inhaltliche Dynamik durch die zugrundeliegende Kollaborationsdynamik bestimmt wird, und zwar so, dass sich die soziale Struktur der entsprechenden inhaltlichen Struktur aufprägt. Dieser Auffassung gemäß führt die Ungleichverteilung der Aktivitäten von Lexikonproduzenten zu einer analogen Ungleichverteilung der im Lexikon dokumentierten Informationseinheiten. Der Beitrag thematisiert Grundlagen zur Beschreibung solcher Systeme ausgehend von einem Parameterraum, welcher die netzwerkanalytische Betrachtung von Wiktionary als Big-Data-Problem darstellt.}, year = 2017 }
-
A. Hoenen, S. Eger, and R. Gehrke, “How Many Stemmata with Root Degree k?,” in Proceedings of the 15th Meeting on the Mathematics of Language, 2017, pp. 11-21.
[BibTeX]@InProceedings{Hoenen:Eger:Gehrke:2017, Author = {Hoenen, Armin and Eger, Steffen and Gehrke, Ralf}, Title = {{How Many Stemmata with Root Degree k?}}, BookTitle = {Proceedings of the 15th Meeting on the Mathematics of Language}, Pages = {11--21}, Publisher = {Association for Computational Linguistics}, location = {London, UK}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/How_Many_Stemmata_with_Root_Degree_k.pdf}, url = {http://aclweb.org/anthology/W17-3402}, year = 2017 }
-
A. Hoenen, “Using Word Embeddings for Computing Distances Between Texts and for Authorship Attribution,” in International Conference on Applications of Natural Language to Information Systems, 2017, pp. 274-277.
[BibTeX]@InProceedings{Hoenen:2017:b, Author = {Hoenen, Armin}, Title = {{Using Word Embeddings for Computing Distances Between Texts and for Authorship Attribution}}, BookTitle = {International Conference on Applications of Natural Language to Information Systems}, Pages = {274--277}, Organization = {Springer}, url = {https://link.springer.com/chapter/10.1007/978-3-319-59569-6_33}, year = 2017 }
-
T. Uslu, W. Hemati, A. Mehler, and D. Baumartz, “TextImager as a Generic Interface to R,” in Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), 2017.
[BibTeX]@InProceedings{Uslu:Hemati:Mehler:Baumartz:2017, Author = {Tolga Uslu and Wahed Hemati and Alexander Mehler and Daniel Baumartz}, Title = {{TextImager} as a Generic Interface to {R}}, BookTitle = {Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017)}, location = {Valencia, Spain}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager.pdf}, year = 2017 }
-
A. Hoenen, “Beyond the tree – a theoretical model of contamination and a software to generate multilingual stemmata,” in Book of Abstracts of the annual conference of the AIUCD 2017, Sapienza, Rome, AIUCD, 2017.
[BibTeX]@InCollection{Hoenen:2017, Author = {Hoenen, Armin}, Title = {{Beyond the tree – a theoretical model of contamination and a software to generate multilingual stemmata}}, BookTitle = {{Book of Abstracts of the annual conference of the AIUCD 2017, Sapienza, Rome}}, Publisher = {AIUCD}, url = {http://aiucd2017.aiucd.it/wp-content/uploads/2017/01/book-of-abstract-AIUCD-2017.pdf}, year = 2017 }
-
A. Lücking, “Indexicals as Weak Descriptors,” in Proceedings of the 12th International Conference on Computational Semantics, Montpellier (France), 2017.
[BibTeX]@InProceedings{Luecking:2017:c, Author = {L\"{u}cking, Andy}, Title = {Indexicals as Weak Descriptors}, BookTitle = {Proceedings of the 12th International Conference on Computational Semantics}, Series = {IWCS 2017}, Address = {Montpellier (France)}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/descriptive-indexicals_rev.pdf}, year = 2017 }
2016 (19)
-
S. Eger, A. Hoenen, and A. Mehler, “Language classification from bilingual word embedding graphs,” in Proceedings of COLING 2016, 2016.
[BibTeX]@InProceedings{Eger:Hoenen:Mehler:2016, Author = {Steffen Eger and Armin Hoenen and Alexander Mehler}, Title = {Language classification from bilingual word embedding graphs}, BookTitle = {Proceedings of COLING 2016}, Publisher = {ACL}, location = {Osaka}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2016/10/eger_hoenen_mehler_COLING2016.pdf}, year = 2016 }
-
W. Hemati, T. Uslu, and A. Mehler, “TextImager: a Distributed UIMA-based System for NLP,” in Proceedings of the COLING 2016 System Demonstrations, 2016.
[BibTeX]@InProceedings{Hemati:Uslu:Mehler:2016, Author = {Wahed Hemati and Tolga Uslu and Alexander Mehler}, Title = {TextImager: a Distributed UIMA-based System for NLP}, BookTitle = {Proceedings of the COLING 2016 System Demonstrations}, Organization = {Federated Conference on Computer Science and Information Systems}, location = {Osaka, Japan}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/TextImager2016.pdf}, year = 2016 }
-
A. Lücking, “Modeling Co-Verbal Gesture Perception in Type Theory with Records,” in Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, Gdansk, Poland, 2016, pp. 383-392. Best Paper Award
[BibTeX]@InProceedings{Luecking:2016:b, Author = {L\"{u}cking, Andy}, Title = {Modeling Co-Verbal Gesture Perception in Type Theory with Records}, BookTitle = {Proceedings of the 2016 Federated Conference on Computer Science and Information Systems}, Editor = {M. Ganzha and L. Maciaszek and M. Paprzycki}, Volume = {8}, Series = {Annals of Computer Science and Information Systems}, Pages = {383-392}, Address = {Gdansk, Poland}, Publisher = {IEEE}, Note = {Best Paper Award}, doi = {10.15439/2016F83}, pdf = {http://annals-csis.org/Volume_8/pliks/83.pdf}, url = {http://annals-csis.org/Volume_8/drp/83.html}, year = 2016 }
-
A. Mehler, T. Uslu, and W. Hemati, “Text2voronoi: An Image-driven Approach to Differential Diagnosis,” in Proceedings of the 5th Workshop on Vision and Language (VL’16) hosted by the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Berlin, 2016.
[BibTeX]@InProceedings{Mehler:Uslu:Hemati:2016, Author = {Alexander Mehler and Tolga Uslu and Wahed Hemati}, Title = {Text2voronoi: An Image-driven Approach to Differential Diagnosis}, BookTitle = {Proceedings of the 5th Workshop on Vision and Language (VL'16) hosted by the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Berlin}, pdf = {https://aclweb.org/anthology/W/W16/W16-3212.pdf}, year = 2016 }
-
S. Eger and A. Mehler, “On the linearity of semantic change: Investigating meaning variation via dynamic graph models,” in Proceedings of ACL 2016, 2016.
[BibTeX]@InProceedings{Eger:Mehler:2016, Author = {Steffen Eger and Alexander Mehler}, Title = {On the linearity of semantic change: {I}nvestigating meaning variation via dynamic graph models}, BookTitle = {Proceedings of ACL 2016}, location = {Berlin}, pdf = {https://www.aclweb.org/anthology/P/P16/P16-2009.pdf}, year = 2016 }
-
S. Eger, T. vor der Brück, and A. Mehler, “A Comparison of Four Character-Level String-to-String Translation Models for (OCR) Spelling Error Correction,” The Prague Bulletin of Mathematical Linguistics, vol. 105, pp. 77-99, 2016.
[BibTeX]@Article{Eger:vorDerBrueck:Mehler:2016, Author = {Eger, Steffen and vor der Brück, Tim and Mehler, Alexander}, Title = {A Comparison of Four Character-Level String-to-String Translation Models for (OCR) Spelling Error Correction}, Journal = {The Prague Bulletin of Mathematical Linguistics}, Volume = {105}, Pages = {77-99}, doi = {10.1515/pralin-2016-0004}, pdf = {https://ufal.mff.cuni.cz/pbml/105/art-eger-vor-der-brueck.pdf}, year = 2016 }
-
A. Hoenen, “Silva Portentosissima – Computer-Assisted Reflections on Bifurcativity in Stemmas,” in Digital Humanities 2016: Conference Abstracts. Jagiellonian University & Pedagogical University, 2016, pp. 557-560.
[Abstract] [BibTeX]In 1928, the philologue Joseph Bédier explored contemporary stemmas and found them to contain a suspiciously large amount of bifurcations. In this paper, the argument is investigated that, with a large amount of lost manuscripts, the amount of bifurcations in the true stemmas would naturally be high because the probability for siblings to survive becomes very low is assessed via a computer simulation.
@InProceedings{Hoenen:2016DH, Author = {Hoenen, Armin}, Title = {{Silva Portentosissima – Computer-Assisted Reflections on Bifurcativity in Stemmas}}, BookTitle = {Digital Humanities 2016: Conference Abstracts. Jagiellonian University \& Pedagogical University}, Series = {DH 2016}, Pages = {557-560}, abstract = {In 1928, the philologue Joseph Bédier explored contemporary stemmas and found them to contain a suspiciously large amount of bifurcations. In this paper, the argument is investigated that, with a large amount of lost manuscripts, the amount of bifurcations in the true stemmas would naturally be high because the probability for siblings to survive becomes very low is assessed via a computer simulation.}, location = {Kraków}, url = {http://dh2016.adho.org/abstracts/311}, year = 2016 }
-
A. Mehler, B. Wagner, and R. Gleim, “Wikidition: Towards A Multi-layer Network Model of Intertextuality,” in Proceedings of DH 2016, 12-16 July, 2016.
[Abstract] [BibTeX]The paper presents Wikidition, a novel text mining tool for generating online editions of text corpora. It explores lexical, sentential and textual relations to span multi-layer networks (linkification) that allow for browsing syntagmatic and paradigmatic relations among the constituents of its input texts. In this way, relations of text reuse can be explored together with lexical relations within the same literary memory information system. Beyond that, Wikidition contains a module for automatic lexiconisation to extract author specific vocabularies. Based on linkification and lexiconisation, Wikidition does not only allow for traversing input corpora on different (lexical, sentential and textual) levels. Rather, its readers can also study the vocabulary of authors on several levels of resolution including superlemmas, lemmas, syntactic words and wordforms. We exemplify Wikidition by a range of literary texts and evaluate it by means of the apparatus of quantitative network analysis.
@InProceedings{Mehler:Wagner:Gleim:2016, Author = {Mehler, Alexander and Wagner, Benno and Gleim, R\"{u}diger}, Title = {Wikidition: Towards A Multi-layer Network Model of Intertextuality}, BookTitle = {Proceedings of DH 2016, 12-16 July}, Series = {DH 2016}, abstract = {The paper presents Wikidition, a novel text mining tool for generating online editions of text corpora. It explores lexical, sentential and textual relations to span multi-layer networks (linkification) that allow for browsing syntagmatic and paradigmatic relations among the constituents of its input texts. In this way, relations of text reuse can be explored together with lexical relations within the same literary memory information system. Beyond that, Wikidition contains a module for automatic lexiconisation to extract author specific vocabularies. Based on linkification and lexiconisation, Wikidition does not only allow for traversing input corpora on different (lexical, sentential and textual) levels. Rather, its readers can also study the vocabulary of authors on several levels of resolution including superlemmas, lemmas, syntactic words and wordforms. We exemplify Wikidition by a range of literary texts and evaluate it by means of the apparatus of quantitative network analysis.}, location = {Kraków}, url = {http://dh2016.adho.org/abstracts/250}, year = 2016 }
-
T. vor der Brück and A. Mehler, “TLT-CRF: A Lexicon-supported Morphological Tagger for Latin Based on Conditional Random Fields,” in Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016.
[BibTeX]@InProceedings{vorderBrueck:Mehler:2016, Author = {vor der Br\"{u}ck, Tim and Mehler, Alexander}, Title = {{TLT-CRF}: A Lexicon-supported Morphological Tagger for {Latin} Based on Conditional Random Fields}, BookTitle = {Proceedings of the 10th International Conference on Language Resources and Evaluation}, Series = {LREC 2016}, location = {{Portoro\v{z} (Slovenia)}}, pdf = {http://www.texttechnologylab.org/wp-content/uploads/2016/04/lrec2016_tagger.pdf}, year = 2016 }
-
S. Eger, R. Gleim, and A. Mehler, “Lemmatization and Morphological Tagging in German and Latin: A comparison and a survey of the state-of-the-art,” in Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016.
[BibTeX]@InProceedings{Eger:Mehler:Gleim:2016, Author = {Eger, Steffen and Gleim, R\"{u}diger and Mehler, Alexander}, Title = {Lemmatization and Morphological Tagging in {German} and {Latin}: A comparison and a survey of the state-of-the-art}, BookTitle = {Proceedings of the 10th International Conference on Language Resources and Evaluation}, Series = {LREC 2016}, location = {Portoro\v{z} (Slovenia)}, pdf = {http://www.texttechnologylab.org/wp-content/uploads/2016/04/lrec_eger_gleim_mehler.pdf}, year = 2016 }
-
A. Lücking, A. Mehler, D. Walther, M. Mauri, and D. Kurfürst, “Finding Recurrent Features of Image Schema Gestures: the FIGURE corpus,” in Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016.
[BibTeX]@InProceedings{Luecking:Mehler:Walther:Mauri:Kurfuerst:2016, Author = {L\"{u}cking, Andy and Mehler, Alexander and Walther, D\'{e}sir\'{e}e and Mauri, Marcel and Kurf\"{u}rst, Dennis}, Title = {Finding Recurrent Features of Image Schema Gestures: the {FIGURE} corpus}, BookTitle = {Proceedings of the 10th International Conference on Language Resources and Evaluation}, Series = {LREC 2016}, location = {Portoro\v{z} (Slovenia)}, pdf = {http://www.texttechnologylab.org/wp-content/uploads/2016/04/lrec2016-gesture-study-final-version-short.pdf}, year = 2016 }
-
A. Lücking, A. Hoenen, and A. Mehler, “TGermaCorp — A (Digital) Humanities Resource for (Computational) Linguistics,” in Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016.
[BibTeX]@InProceedings{Luecking:Hoenen:Mehler:2016, Author = {L\"{u}cking, Andy and Hoenen, Armin and Mehler, Alexander}, Title = {{TGermaCorp} -- A (Digital) Humanities Resource for (Computational) Linguistics}, BookTitle = {Proceedings of the 10th International Conference on Language Resources and Evaluation}, Series = {LREC 2016}, islrn = {536-382-801-278-5}, location = {Portoro\v{z} (Slovenia)}, pdf = {http://www.texttechnologylab.org/wp-content/uploads/2016/04/lrec2016-ttgermacorp-final.pdf}, year = 2016 }
-
B. Wagner, A. Mehler, and H. Biber, “Transbiblionome Daten in der Literaturwissenschaft. Texttechnologische Erschließung und digitale Visualisierung intertextueller Beziehungen digitaler Korpora,” in DHd 2016, 2016.
[BibTeX]@InProceedings{Wagner:Mehler:Biber:2016, Author = {Wagner, Benno and Mehler, Alexander and Biber, Hanno}, Title = {{Transbiblionome Daten in der Literaturwissenschaft. Texttechnologische Erschließung und digitale Visualisierung intertextueller Beziehungen digitaler Korpora}}, BookTitle = {DHd 2016}, url = {http://www.dhd2016.de/abstracts/sektionen-005.html#index.xml-body.1_div.4}, year = 2016 }
-
A. Mehler, R. Gleim, T. vor der Brück, W. Hemati, T. Uslu, and S. Eger, “Wikidition: Automatic Lexiconization and Linkification of Text Corpora,” Information Technology, vol. 58, pp. 70-79, 2016.
[Abstract] [BibTeX]We introduce a new text technology, called Wikidition, which automatically generates large scale editions of corpora of natural language texts. Wikidition combines a wide range of text mining tools for automatically linking lexical, sentential and textual units. This includes the extraction of corpus-specific lexica down to the level of syntactic words and their grammatical categories. To this end, we introduce a novel measure of text reuse and exemplify Wikidition by means of the capitularies, that is, a corpus of Medieval Latin texts.
@Article{Mehler:et:al:2016, Author = {Alexander Mehler and Rüdiger Gleim and Tim vor der Brück and Wahed Hemati and Tolga Uslu and Steffen Eger}, Title = {Wikidition: Automatic Lexiconization and Linkification of Text Corpora}, Journal = {Information Technology}, Volume = {58}, Pages = {70-79}, abstract = {We introduce a new text technology, called Wikidition, which automatically generates large scale editions of corpora of natural language texts. Wikidition combines a wide range of text mining tools for automatically linking lexical, sentential and textual units. This includes the extraction of corpus-specific lexica down to the level of syntactic words and their grammatical categories. To this end, we introduce a novel measure of text reuse and exemplify Wikidition by means of the capitularies, that is, a corpus of Medieval Latin texts.}, doi = {10.1515/itit-2015-0035}, year = 2016 }
-
A. Hoenen, “Wikipedia Titles As Noun Tag Predictors,” in Proceedings of the 10th International Conference on Language Resources and Evaluation, 2016.
[BibTeX]@InProceedings{Hoenen:2016x, Author = {Hoenen, Armin}, Title = {{Wikipedia Titles As Noun Tag Predictors}}, BookTitle = {Proceedings of the 10th International Conference on Language Resources and Evaluation}, Series = {LREC 2016}, location = {Portoro\v{z} (Slovenia)}, pdf = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/18_Paper.pdf}, year = 2016 }
-
A. Hoenen, “Das erste dynamische Stemma, Pionier des digitalen Zeitalters?,” in Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum, 2016.
[BibTeX]@InProceedings{Hoenen:2016y, Author = {Hoenen, Armin}, Title = {Das erste dynamische Stemma, Pionier des digitalen Zeitalters?}, BookTitle = {Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum}, url = {http://www.dhd2016.de/abstracts/posters-060.html}, year = 2016 }
-
“Corpora and Resources for (Historical) Low Resource Languages,” , vol. 31, iss. 2, 2016.
[BibTeX]@collection{GSCL:JLCL:2016:2, bibsource = {GSCL, http://www.gscl.info/}, editor = {Armin Hoenen and Alexander Mehler and Jost Gippert}, image = {https://www.texttechnologylab.org/wp-content/uploads/2017/10/Titelblatt-Heft2-2016.png}, issn = {2190-6858}, number = {2}, pdf = {http://www.jlcl.org/2016_Heft2/Heft2-2016.pdf}, publisher = {JLCL}, title = {{Corpora and Resources for (Historical) Low Resource Languages}}, volume = {31}, year = 2016 }
-
A. Hoenen, A. Mehler, and J. Gippert, “Editorial,” JLCL, vol. 31, iss. 2, p. iii–iv, 2016.
[BibTeX]@Article{Hoenen:Mehler:Gippert:2016, Author = {Armin Hoenen and Alexander Mehler and Jost Gippert}, Title = {{Editorial}}, Journal = {JLCL}, Volume = {31}, Number = {2}, Pages = {iii--iv}, pdf = {http://www.jlcl.org/2016_Heft2/Heft2-2016.pdf}, year = 2016 }
-
A. Hoenen and L. Samushia, “Gepi: An Epigraphic Corpus for Old Georgian and a Tool Sketch for Aiding Reconstruction,” JLCL, vol. 31, iss. 2, pp. 25-38, 2016.
[BibTeX]@Article{Hoenen:Samushia:2016, Author = {Armin Hoenen and Lela Samushia}, Title = {{Gepi: An Epigraphic Corpus for Old Georgian and a Tool Sketch for Aiding Reconstruction}}, Journal = {JLCL}, Volume = {31}, Number = {2}, Pages = {25--38}, year = 2016 }
2015 (25)
-
A. Hoenen and F. Mader, “A New LMF Schema Application by Example of an Austrian Lexicon Applied to the Historical Corpus of the Writer Hugo von Hofmannsthal,” in Historical Corpora, 2015.
[BibTeX]@InProceedings{Hoenen:Mader:2015, Author = {Hoenen, Armin and Mader, Franziska}, Title = {A New LMF Schema Application by Example of an Austrian Lexicon Applied to the Historical Corpus of the Writer Hugo von Hofmannsthal}, BookTitle = {Historical Corpora}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/HoenenMader2013-a-new-lmf-schema-application.pdf}, website = {http://www.narr-shop.de/historical-corpora.html}, year = 2015 }
-
Text Mining: From Ontology Learning to Automated Text Processing Applications. Festschrift in Honor of Gerhard Heyer, C. Biemann and A. Mehler, Eds., Heidelberg: Springer, 2015.
[BibTeX]@Book{Biemann:Mehler:2015, Editor = {Biemann, Chris and Mehler, Alexander}, Title = {{Text Mining: From Ontology Learning to Automated Text Processing Applications. Festschrift in Honor of Gerhard Heyer}}, Publisher = {Springer}, Series = {Theory and Applications of Natural Language Processing}, Address = {Heidelberg}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/TextMiningsmall.jpg}, year = 2015 }
-
M. Z. Islam, “Multilingual text classification using information-theoretic features,” PhD Thesis, 2015.
[Abstract] [BibTeX]The number of multilingual texts in the World Wide Web (WWW) is increasing dramatically and a multilingual economic zone like the European Union (EU) requires the availability of multilingual Natural Language Processing (NLP) tools. Due to a rapid development of NLP tools, many lexical, syntactic, semantic and other linguistic features have been used in different NLP applications. However, there are some situations where these features can not be used due the application type or unavailability of NLP resources for some of the languages. That is why an application that is intended to handle multilingual texts must have features that are not dependent on a particular language and specific linguistic tools. In this thesis, we will focus on two such applications: text readability and source and translation classification. In this thesis, we provide 18 features that are not only suitable for both applications, but are also language and linguistic tools independent. In order to build a readability classifier, we use texts from three different languages: English, German and Bangla. Our proposed features achieve a classification accuracy that is comparable with a classifier using 40 linguistic features. The readability classifier achieves a classification F-score of 74.21% on the English Wikipedia corpus, an F-score of 75.47% on the English textbook corpus, an F-score of 86.46% on the Bangla textbook corpus and an F-score of 86.26% on the German GEO/GEOLino corpus. We used more than two million sentence pairs from 21 European languages in order to build the source and translation classifier. The classifier using the same eighteen features achieves a classification accuracy of 86.63%. We also used the same features to build a classifier that classifies translated texts based on their origin. The classifier achieves classification accuracy of 75% for texts from 10 European languages. In this thesis, we also provide four different corpora, three for text readability analysis and one for corpus based translation studies.
@phdthesis{Islam:2015, author = {Mohammad Zahurul Islam}, title = {Multilingual text classification using information-theoretic features}, pages = {189}, year = {2015}, pdf = {http://publikationen.ub.uni-frankfurt.de/files/38157/thesis.pdf}, abstract = {The number of multilingual texts in the World Wide Web (WWW) is increasing dramatically and a multilingual economic zone like the European Union (EU) requires the availability of multilingual Natural Language Processing (NLP) tools. Due to a rapid development of NLP tools, many lexical, syntactic, semantic and other linguistic features have been used in different NLP applications. However, there are some situations where these features can not be used due the application type or unavailability of NLP resources for some of the languages. That is why an application that is intended to handle multilingual texts must have features that are not dependent on a particular language and specific linguistic tools. In this thesis, we will focus on two such applications: text readability and source and translation classification. In this thesis, we provide 18 features that are not only suitable for both applications, but are also language and linguistic tools independent. In order to build a readability classifier, we use texts from three different languages: English, German and Bangla. Our proposed features achieve a classification accuracy that is comparable with a classifier using 40 linguistic features. The readability classifier achieves a classification F-score of 74.21% on the English Wikipedia corpus, an F-score of 75.47% on the English textbook corpus, an F-score of 86.46% on the Bangla textbook corpus and an F-score of 86.26% on the German GEO/GEOLino corpus. We used more than two million sentence pairs from 21 European languages in order to build the source and translation classifier. The classifier using the same eighteen features achieves a classification accuracy of 86.63%. We also used the same features to build a classifier that classifies translated texts based on their origin. The classifier achieves classification accuracy of 75% for texts from 10 European languages. In this thesis, we also provide four different corpora, three for text readability analysis and one for corpus based translation studies.} }
-
N. Dundua, A. Hoenen, and L. Samushia, “A Parallel Corpus of the Old Georgian Gospel Manuscripts and their Stemmatology,” The Georgian Journal for Language Logic Computation, vol. IV, pp. 176-185, 2015.
[BibTeX]@Article{Dundua:Hoenen:Samushia:2015, Author = {Dundua, Natia and Hoenen, Armin and Samushia, Lela}, Title = {{A Parallel Corpus of the Old Georgian Gospel Manuscripts and their Stemmatology}}, Journal = {The Georgian Journal for Language Logic Computation}, Volume = {IV}, Pages = {176-185}, publisher = {CLLS, Tbilisi State University and Kurt G{\"o}del Society}, year = 2015 }
-
T. vor der Brück, S. Eger, and A. Mehler, “Complex Decomposition of the Negative Distance Kernel,” in IEEE International Conference on Machine Learning and Applications, 2015.
[BibTeX]@InProceedings{vor:der:Bruck:Eger:Mehler:2015, Author = {vor der Br{\"u}ck, Tim and Eger, Steffen and Mehler, Alexander}, Title = {Complex Decomposition of the Negative Distance Kernel}, BookTitle = {IEEE International Conference on Machine Learning and Applications}, location = {Miami, Florida, USA}, year = 2015 }
-
S. Eger, “Do we need bigram alignment models? On the effect of alignment quality on transduction accuracy in G2P,” in Proceedings of EMNLP, 2015.
[BibTeX]@InProceedings{Eger:2015_EMNLP, Author = {Eger, Steffen}, Title = {Do we need bigram alignment models? On the effect of alignment quality on transduction accuracy in G2P}, BookTitle = {Proceedings of EMNLP}, year = 2015, pdf = {https://www.aclweb.org/anthology/D15-1139} }
-
T. vor der Brück and S. Eger, “Deriving a primal form for the quadratic power kernel,” in Proceedings of the 38th German Conference on Artificial Intelligence (KI), 2015.
[BibTeX]@InProceedings{vorDerBrueck:Eger:2015, Author = {vor der Brück, Tim and Eger, Steffen}, Title = {Deriving a primal form for the quadratic power kernel}, BookTitle = {Proceedings of the 38th German Conference on Artificial Intelligence ({KI})}, year = 2015 }
-
S. Eger, “Improving G2P from Wiktionary and other (web) resources,” in Proceedings of Interspeech, 2015.
[BibTeX]@InProceedings{Eger:2015_Interspeech, Author = {Eger, Steffen}, Title = {Improving G2P from Wiktionary and other (web) resources}, BookTitle = {Proceedings of Interspeech}, pdf = {https://pdfs.semanticscholar.org/bba8/30015d9cbfc40b975c25d0ec186280da6ab0.pdf}, year = 2015 }
-
S. Eger, T. vor der Brück, and A. Mehler, “Lexicon-assisted tagging and lemmatization in Latin: A comparison of six taggers and two lemmatization methods,” in Proceedings of the 9th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH 2015), Beijing, China, 2015.
[BibTeX]@InProceedings{Eger:vor:der:Brueck:Mehler:2015, Author = {Eger, Steffen and vor der Brück, Tim and Mehler, Alexander}, Title = {Lexicon-assisted tagging and lemmatization in {Latin}: A comparison of six taggers and two lemmatization methods}, BookTitle = {Proceedings of the 9th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities ({LaTeCH 2015})}, Address = {Beijing, China}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Lexicon-assisted_tagging.pdf}, year = 2015 }
-
Towards a Theoretical Framework for Analyzing Complex Linguistic Networks, A. Mehler, A. Lücking, S. Banisch, P. Blanchard, and B. Frank-Job, Eds., Springer, 2015.
[BibTeX]@Book{Mehler:Luecking:Banisch:Blanchard:Frank-Job:2015, Editor = {Mehler, Alexander and Lücking, Andy and Banisch, Sven and Blanchard, Philippe and Frank-Job, Barbara}, Title = {Towards a Theoretical Framework for Analyzing Complex Linguistic Networks}, Publisher = {Springer}, Series = {Understanding Complex Systems}, adress = {Berlin and New York}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/UCS_17-2-tmp.png}, isbn = {978-36-662-47237-8}, year = 2015 }
-
A. Mehler and R. Gleim, “Linguistic Networks — An Online Platform for Deriving Collocation Networks from Natural Language Texts,” in Towards a Theoretical Framework for Analyzing Complex Linguistic Networks, A. Mehler, A. Lücking, S. Banisch, P. Blanchard, and B. Frank-Job, Eds., Springer, 2015.
[BibTeX]@InCollection{Mehler:Gleim:2015:a, Author = {Mehler, Alexander and Gleim, Rüdiger}, Title = {Linguistic Networks -- An Online Platform for Deriving Collocation Networks from Natural Language Texts}, BookTitle = {Towards a Theoretical Framework for Analyzing Complex Linguistic Networks}, Publisher = {Springer}, Editor = {Mehler, Alexander and Lücking, Andy and Banisch, Sven and Blanchard, Philippe and Frank-Job, Barbara}, Series = {Understanding Complex Systems}, year = 2015 }
-
S. Eger, “Multiple Many-To-Many Sequence Alignment For Combining String-Valued Variables: A G2P Experiment,” in ACL, 2015.
[BibTeX]@InProceedings{Eger:2015_ACL, Author = {Eger, Steffen}, Title = {Multiple Many-To-Many Sequence Alignment For Combining String-Valued Variables: A G2P Experiment}, BookTitle = {ACL}, Publisher = {Association for Computational Linguistics}, year = 2015 }
-
S. Eger, “Designing and comparing G2P-type lemmatizers for a morphology-rich language.” 2015.
[BibTeX]@InProceedings{Eger:2015_SFCM, Author = {Eger, Steffen}, Title = {Designing and comparing G2P-type lemmatizers for a morphology-rich language}, Publisher = {Fourth International Workshop on Systems and Frameworks for Computational Morphology}, year = 2015 }
-
S. Eger, N. Schenk, and A. Mehler, “Towards Semantic Language Classification: Inducing and Clustering Semantic Association Networks from Europarl,” in Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics, 2015, pp. 127-136.
[BibTeX]@InProceedings{Eger:Schenk:Mehler:2015, Author = {Eger, Steffen and Schenk, Niko and Mehler, Alexander}, Title = {Towards Semantic Language Classification: Inducing and Clustering Semantic Association Networks from Europarl}, BookTitle = {Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics}, Pages = {127--136}, Publisher = {Association for Computational Linguistics}, month = {June}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/starsem2015-corrected-version.pdf}, url = {http://www.aclweb.org/anthology/S15-1014}, year = 2015 }
-
S. Eger, “Identities for Partial Bell Polynomials Derived from Identities for Weighted Integer Compositions.,” Aequationes Mathematicae, 2015.
[BibTeX]@Article{Eger:2015b, Author = {Eger, Steffen}, Title = {Identities for Partial Bell Polynomials Derived from Identities for Weighted Integer Compositions.}, Journal = {Aequationes Mathematicae}, doi = {10.1007/s00010-015-0338-2}, year = 2015 }
-
S. Eger, “Some Elementary Congruences for the Number of Weighted Integer Compositions.,” Journal of Integer Sequences (electronic only), vol. 18, iss. 4, 2015.
[BibTeX]@Article{Eger:2015a, Author = {Eger, Steffen}, Title = {Some Elementary Congruences for the Number of Weighted Integer Compositions.}, Journal = {Journal of Integer Sequences (electronic only)}, Volume = {18}, Number = {4}, pdf = {https://cs.uwaterloo.ca/journals/JIS/VOL18/Eger/eger11.pdf}, publisher = {School of Computer Science, University of Waterloo, Waterloo, ON}, year = 2015 }
-
A. Lücking, T. Pfeiffer, and H. Rieser, “Pointing and Reference Reconsidered,” Journal of Pragmatics, vol. 77, pp. 56-79, 2015.
[Abstract] [BibTeX]Current semantic theory on indexical expressions claims that demonstratively used indexicals such as this lack a referent-determining meaning but instead rely on an accompanying demonstration act like a pointing gesture. While this view allows to set up a sound logic of demonstratives, the direct-referential role assigned to pointing gestures has never been scrutinized thoroughly in semantics or pragmatics. We investigate the semantics and pragmatics of co-verbal pointing from a foundational perspective combining experiments, statistical investigation, computer simulation and theoretical modeling techniques in a novel manner. We evaluate various referential hypotheses with a corpus of object identification games set up in experiments in which body movement tracking techniques have been extensively used to generate precise pointing measurements. Statistical investigation and computer simulations show that especially distal areas in the pointing domain falsify the semantic direct-referential hypotheses concerning pointing gestures. As an alternative, we propose that reference involving pointing rests on a default inference which we specify using the empirical data. These results raise numerous problems for classical semantics–pragmatics interfaces: we argue for pre-semantic pragmatics in order to account for inferential reference in addition to classical post-semantic Gricean pragmatics.
@Article{Luecking:Pfeiffer:Rieser:2015, Author = {Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes}, Title = {Pointing and Reference Reconsidered}, Journal = {Journal of Pragmatics}, Volume = {77}, Pages = {56-79}, abstract = {Current semantic theory on indexical expressions claims that demonstratively used indexicals such as this lack a referent-determining meaning but instead rely on an accompanying demonstration act like a pointing gesture. While this view allows to set up a sound logic of demonstratives, the direct-referential role assigned to pointing gestures has never been scrutinized thoroughly in semantics or pragmatics. We investigate the semantics and pragmatics of co-verbal pointing from a foundational perspective combining experiments, statistical investigation, computer simulation and theoretical modeling techniques in a novel manner. We evaluate various referential hypotheses with a corpus of object identification games set up in experiments in which body movement tracking techniques have been extensively used to generate precise pointing measurements. Statistical investigation and computer simulations show that especially distal areas in the pointing domain falsify the semantic direct-referential hypotheses concerning pointing gestures. As an alternative, we propose that reference involving pointing rests on a default inference which we specify using the empirical data. These results raise numerous problems for classical semantics–pragmatics interfaces: we argue for pre-semantic pragmatics in order to account for inferential reference in addition to classical post-semantic Gricean pragmatics.}, doi = {10.1016/j.pragma.2014.12.013}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Luecking_Pfeiffer_Rieser_Pointing_and_Reference_Reconsiderd.pdf}, website = {http://www.sciencedirect.com/science/article/pii/S037821661500003X}, year = 2015 }
-
A. Mehler, T. vor der Brück, R. Gleim, and T. Geelhaar, “Towards a Network Model of the Coreness of Texts: An Experiment in Classifying Latin Texts using the TTLab Latin Tagger,” in Text Mining: From Ontology Learning to Automated text Processing Applications, C. Biemann and A. Mehler, Eds., Berlin/New York: Springer, 2015, pp. 87-112.
[Abstract] [BibTeX]The analysis of longitudinal corpora of historical texts requires the integrated development of tools for automatically preprocessing these texts and for building representation models of their genre- and register-related dynamics. In this chapter we present such a joint endeavor that ranges from resource formation via preprocessing to network-based text representation and classification. We start with presenting the so-called TTLab Latin Tagger (TLT) that preprocesses texts of classical and medieval Latin. Its lexical resource in the form of the Frankfurt Latin Lexicon (FLL) is also briefly introduced. As a first test case for showing the expressiveness of these resources, we perform a tripartite classification task of authorship attribution, genre detection and a combination thereof. To this end, we introduce a novel text representation model that explores the core structure (the so-called coreness) of lexical network representations of texts. Our experiment shows the expressiveness of this representation format and mediately of our Latin preprocessor.
@InCollection{Mehler:Brueck:Gleim:Geelhaar:2015, Author = {Mehler, Alexander and vor der Brück, Tim and Gleim, Rüdiger and Geelhaar, Tim}, Title = {Towards a Network Model of the Coreness of Texts: An Experiment in Classifying Latin Texts using the TTLab Latin Tagger}, BookTitle = {Text Mining: From Ontology Learning to Automated text Processing Applications}, Publisher = {Springer}, Editor = {Chris Biemann and Alexander Mehler}, Series = {Theory and Applications of Natural Language Processing}, Pages = {87-112}, Address = {Berlin/New York}, abstract = {The analysis of longitudinal corpora of historical texts requires the integrated development of tools for automatically preprocessing these texts and for building representation models of their genre- and register-related dynamics. In this chapter we present such a joint endeavor that ranges from resource formation via preprocessing to network-based text representation and classification. We start with presenting the so-called TTLab Latin Tagger (TLT) that preprocesses texts of classical and medieval Latin. Its lexical resource in the form of the Frankfurt Latin Lexicon (FLL) is also briefly introduced. As a first test case for showing the expressiveness of these resources, we perform a tripartite classification task of authorship attribution, genre detection and a combination thereof. To this end, we introduce a novel text representation model that explores the core structure (the so-called coreness) of lexical network representations of texts. Our experiment shows the expressiveness of this representation format and mediately of our Latin preprocessor.}, website = {http://link.springer.com/chapter/10.1007/978-3-319-12655-5_5}, year = 2015 }
-
A. Hoenen, “Das artifizielle Manuskriptkorpus TASCFE,” in Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum, 2015.
[BibTeX]@InProceedings{Hoenen:2015, Author = {Hoenen, Armin}, Title = {Das artifizielle Manuskriptkorpus TASCFE}, BookTitle = {Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Hoenen_tascfeDH2015.pdf}, year = 2015 }
-
R. Gleim and A. Mehler, “TTLab Preprocessor – Eine generische Web-Anwendung für die Vorverarbeitung von Texten und deren Evaluation,” in Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum, 2015.
[BibTeX]@InProceedings{Gleim:Mehler:2015, Author = {Gleim, Rüdiger and Mehler, Alexander}, Title = {TTLab Preprocessor – Eine generische Web-Anwendung für die Vorverarbeitung von Texten und deren Evaluation}, BookTitle = {Accepted in the Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Gleim_Mehler_PrePro_DHGraz2015.pdf}, year = 2015 }
-
G. Abrami, A. Mehler, and S. Zeunert, “Ontologiegestütze geisteswissenschaftliche Annotationen mit dem OWLnotator,” in Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum, 2015.
[BibTeX]@InProceedings{Abrami:Mehler:Zeunert:2015:a, Author = {Abrami, Giuseppe and Mehler, Alexander and Zeunert, Susanne}, Title = {Ontologiegestütze geisteswissenschaftliche Annotationen mit dem OWLnotator}, BookTitle = {Proceedings of the Jahrestagung der Digital Humanities im deutschsprachigen Raum}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Abrami_Mehler_Zeunert_DHd_2015_abstract.pdf}, year = 2015 }
-
G. Abrami, A. Mehler, and D. Pravida, “Fusing Text and Image Data with the Help of the OWLnotator,” in Human Interface and the Management of Information. Information and Knowledge Design, S. Yamamoto, Ed., Springer International Publishing, 2015, vol. 9172, pp. 261-272.
[BibTeX]@InCollection{Abrami:Mehler:Pravida:2015:b, Author = {Abrami, Giuseppe and Mehler, Alexander and Pravida, Dietmar}, Title = {Fusing Text and Image Data with the Help of the OWLnotator}, BookTitle = {Human Interface and the Management of Information. Information and Knowledge Design}, Publisher = {Springer International Publishing}, Editor = {Yamamoto, Sakae}, Volume = {9172}, Series = {Lecture Notes in Computer Science}, Pages = {261-272}, doi = {10.1007/978-3-319-20612-7_25}, isbn = {978-3-319-20611-0}, language = {English}, website = {http://dx.doi.org/10.1007/978-3-319-20612-7_25}, year = 2015 }
-
A. Hoenen, “Lachmannian Archetype Reconstruction for Ancient Manuscript Corpora,” in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), 2015. Citation: Trovato is published in 2014 not in 2009.
[Abstract] [BibTeX]Two goals are targeted by computer philology for ancient manuscript corpora: firstly, making an edition, that is roughly speaking one text version representing the whole corpus, which contains variety induced through copy errors and other processes and secondly, producing a stemma. A stemma is a graph-based visualization of the copy history with manuscripts as nodes and copy events as edges. Its root, the so-called archetype is the supposed original text or urtext from which all subsequent copies are made. Our main contribution is to present one of the first computational approaches to automatic archetype reconstruction and to introduce the first text-based evaluation for automatically produced archetypes. We compare a philologically generated archetype with one generated by bio-informatic software.
@InProceedings{Hoenen:2015a, Author = {Hoenen, Armin}, Title = {Lachmannian Archetype Reconstruction for Ancient Manuscript Corpora}, BookTitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT)}, Note = {Citation: Trovato is published in 2014 not in 2009.}, abstract = {Two goals are targeted by computer philology for ancient manuscript corpora: firstly, making an edition, that is roughly speaking one text version representing the whole corpus, which contains variety induced through copy errors and other processes and secondly, producing a stemma. A stemma is a graph-based visualization of the copy history with manuscripts as nodes and copy events as edges. Its root, the so-called archetype is the supposed original text or urtext from which all subsequent copies are made. Our main contribution is to present one of the first computational approaches to automatic archetype reconstruction and to introduce the first text-based evaluation for automatically produced archetypes. We compare a philologically generated archetype with one generated by bio-informatic software.}, website = {http://www.aclweb.org/anthology/N15-1127}, year = 2015 }
-
A. Hoenen, “Simulating Misreading,” in Proceedings of the 20TH INTERNATIONAL CONFERENCE ON APPLICATIONS OF NATURAL LANGUAGE TO INFORMATION SYSTEMS (NLDB), 2015.
[Abstract] [BibTeX]Physical misreading (as opposed to interpretational misreading) is an unnoticed substitution in silent reading. Especially for legally important documents or instruction manuals, this can lead to serious consequences. We present a prototype of an automatic highlighter targeting words which can most easily be misread in a given text using a dynamic orthographic neighbour concept. We propose measures of fit of a misread token based on Natural Language Processing and detect a list of short most easily misread tokens in the English language. We design a highlighting scheme for avoidance of misreading.
@InProceedings{Hoenen:2015b, Author = {Hoenen, Armin}, Title = {Simulating Misreading}, BookTitle = {Proceedings of the 20TH INTERNATIONAL CONFERENCE ON APPLICATIONS OF NATURAL LANGUAGE TO INFORMATION SYSTEMS (NLDB)}, abstract = {Physical misreading (as opposed to interpretational misreading) is an unnoticed substitution in silent reading. Especially for legally important documents or instruction manuals, this can lead to serious consequences. We present a prototype of an automatic highlighter targeting words which can most easily be misread in a given text using a dynamic orthographic neighbour concept. We propose measures of fit of a misread token based on Natural Language Processing and detect a list of short most easily misread tokens in the English language. We design a highlighting scheme for avoidance of misreading.}, website = {http://link.springer.com/chapter/10.1007/978-3-319-19581-0_34}, year = 2015 }
-
G. Abrami, M. Freiberg, and P. Warner, “Managing and Annotating Historical Multimodal Corpora with the eHumanities Desktop – An outline of the current state of the LOEWE project Illustrations of Goethe s Faust,” in Historical Corpora, 2015, pp. 353-363.
[Abstract] [BibTeX]Text corpora are structured sets of text segments that can be annotated or interrelated. Expanding on this, we can define a database of images as an iconographic multimodal corpus with annotated images and the relations between images as well as between images and texts. The Goethe-Museum in Frankfurt holds a significant collection of art work and texts relating to Goethe’s Faust from the early 19th century until the present. In this project we create a database containing digitized items from this collection, and extend a tool, the ImageDB in the eHumanities Desktop, to annotate and provide relations between resources. This article gives an overview of the project and provides some technical details. Furthermore we show newly implemented features, explain the challenge of creating an ontology on multimodal corpora and give a forecast for future work.
@InProceedings{Abrami:Freiberg:Warner:2015, Author = {Abrami, Giuseppe and Freiberg, Michael and Warner, Paul}, Title = {Managing and Annotating Historical Multimodal Corpora with the eHumanities Desktop - An outline of the current state of the LOEWE project Illustrations of Goethe s Faust}, BookTitle = {Historical Corpora}, Pages = {353 - 363}, abstract = {Text corpora are structured sets of text segments that can be annotated or interrelated. Expanding on this, we can define a database of images as an iconographic multimodal corpus with annotated images and the relations between images as well as between images and texts. The Goethe-Museum in Frankfurt holds a significant collection of art work and texts relating to Goethe’s Faust from the early 19th century until the present. In this project we create a database containing digitized items from this collection, and extend a tool, the ImageDB in the eHumanities Desktop, to annotate and provide relations between resources. This article gives an overview of the project and provides some technical details. Furthermore we show newly implemented features, explain the challenge of creating an ontology on multimodal corpora and give a forecast for future work.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/AbramiFreibergWarner_HC_2012.pdf}, website = {http://www.narr-shop.de/historical-corpora.html}, year = 2015 }
2014 (13)
-
A. Hoenen, “Stemmatology, an interdisciplinary endeavour,” in Book of Abstracts zum DHd Workshop Informatik und die Digital Humanities, DHd, 2014.
[BibTeX]@InCollection{Hoenen:2014plz, Author = {Hoenen, Armin}, Title = {{Stemmatology, an interdisciplinary endeavour}}, BookTitle = {{Book of Abstracts zum DHd Workshop Informatik und die Digital Humanities}}, Publisher = {DHd}, url = {http://dhd-wp.hab.de/files/book_of_abstracts.pdf}, year = 2014 }
-
X. Chen, “Language as a whole — A new framework for linguistic knowledge integration: Comment on “Approaching human language with complex networks” by Cong and Liu,” Physics of Life Reviews, vol. 11, iss. 4, pp. 628-629, 2014.
[BibTeX]@Article{Chen:2014:a, Author = {Chen, Xinying}, Title = {Language as a whole -- A new framework for linguistic knowledge integration: Comment on "Approaching human language with complex networks" by {Cong} and {Liu}}, Journal = {Physics of Life Reviews}, Volume = {11}, Number = {4}, Pages = {628-629}, doi = {10.1016/j.plrev.2014.07.011}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Language-as-a-whole-Chen.pdf}, url = {http://www.sciencedirect.com/science/article/pii/S1571064514001249}, year = 2014 }
-
T. Gong, Y. W. Lam, X. Chen, and M. Zhang, “Review: Evolutionary Linguistics in the Past Two Decades — EVOLANG10: the 10th International Conference on Language Evolution,” Journal of Chinese Linguistics, vol. 42, iss. 2, pp. 499-530, 2014.
[BibTeX]@Article{Gong:Lam:Chen:Zhang:2014, Author = {Gong, Tao and Lam, Yau Wai and Chen, Xinying and Zhang, Menghan}, Title = {Review: Evolutionary Linguistics in the Past Two Decades -- EVOLANG10: the 10th International Conference on Language Evolution}, Journal = {Journal of Chinese Linguistics}, Volume = {42}, Number = {2}, Pages = {499-530}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/JCL-EvolangReview.pdf}, year = 2014 }
-
G. Abrami, A. Mehler, D. Pravida, and S. Zeunert, “Rubrik: Neues aus dem Netz,” Kunstchronik, vol. 12, p. 623, 2014.
[BibTeX]@Article{Abrami:Mehler:Pravida:Zeunert:2014, Author = {Abrami, Giuseppe and Mehler, Alexander and Pravida, Dietmar and Zeunert, Susanne}, Title = {Rubrik: Neues aus dem Netz}, Journal = {Kunstchronik}, Volume = {12}, Pages = {623}, address = {München}, month = {12}, publisher = {Zentralinstitut für Kunstgeschichte}, website = {http://www.zikg.eu/publikationen/laufende-publikationen/kunstchronik}, year = 2014 }
-
S. Eger, “A proof of the Mann-Shanks primality criterion conjecture for extended binomial coefficients,” Integers: The Electronic Journal of Combinatorial Number Theory, vol. 14, 2014.
[Abstract] [BibTeX]We show that the Mann-Shanks primality criterion holds for weighted extended binomial coefficients (which count the number of weighted integer compositions), not only for the ordinary binomial coefficients.
@Article{Eger:2014:a, Author = {Eger, Steffen}, Title = {A proof of the Mann-Shanks primality criterion conjecture for extended binomial coefficients}, Journal = {Integers: The Electronic Journal of Combinatorial Number Theory}, Volume = {14}, abstract = {We show that the Mann-Shanks primality criterion holds for weighted extended binomial coefficients (which count the number of weighted integer compositions), not only for the ordinary binomial coefficients.}, pdf = {http://www.emis.de/journals/INTEGERS/papers/o60/o60.pdf}, website = {http://www.emis.de/journals/INTEGERS/vol14.html}, year = 2014 }
-
S. Eger, “Stirling’s approximation for central extended binomial coefficients.,” The American Mathematical Monthly, vol. 121, iss. 4, pp. 344-349, 2014.
[Abstract] [BibTeX]We derive asymptotic formulas for central extended binomial coefficients, which are generalizations of binomial coefficients, using the distribution of the sum of independent discrete uniform random variables with the Central Limit Theorem and a local limit variant.
@Article{Eger:2014:b, Author = {Eger, Steffen}, Title = {Stirling's approximation for central extended binomial coefficients.}, Journal = {The American Mathematical Monthly}, Volume = {121}, Number = {4}, Pages = {344-349}, abstract = {We derive asymptotic formulas for central extended binomial coefficients, which are generalizations of binomial coefficients, using the distribution of the sum of independent discrete uniform random variables with the Central Limit Theorem and a local limit variant.}, website = {http://www.jstor.org/stable/10.4169/amer.math.monthly.121.04.344}, year = 2014 }
-
A. Mehler, “On the Expressiveness, Validity and Reproducibility of Models of Language Evolution. Comment on ‘Modelling language evolution: Examples and predictions’ by Tao Gong, Shuai Lan, and Menghan Zhang,” Physics of Life Review, 2014.
[BibTeX]@Article{Mehler:2014, Author = {Mehler, Alexander}, Title = {On the Expressiveness, Validity and Reproducibility of Models of Language Evolution. Comment on 'Modelling language evolution: Examples and predictions' by Tao Gong, Shuai Lan, and Menghan Zhang}, Journal = {Physics of Life Review}, abstract = {}, pdf = {http://www.sciencedirect.com/science/article/pii/S1571064514000529/pdfft?md5=6a2cbbfc083d7bc3adfd26d431cc55d8&pid=1-s2.0-S1571064514000529-main.pdf}, website = {https://www.researchgate.net/publication/261290946_On_the_expressiveness_validity_and_reproducibility_of_models_of_language_evolution_Comment_on_Modelling_language_evolution_Examples_and_predictions_by_Tao_Gong_Shuai_Lan_and_Menghan_Zhang}, year = 2014 }
-
C. Biemann, G. R. Crane, C. D. Fellbaum, and A. Mehler, “Computational Humanities – bridging the gap between Computer Science and Digital Humanities (Dagstuhl Seminar 14301),” Dagstuhl Reports, vol. 4, iss. 7, pp. 80-111, 2014.
[Abstract] [BibTeX]Research in the field of Digital Humanities, also known as Humanities Computing, has seen a steady increase over the past years. Situated at the intersection of computing science and the humanities, present efforts focus on making resources such as texts, images, musical pieces and other semiotic artifacts digitally available, searchable and analysable. To this end, computational tools enabling textual search, visual analytics, data mining, statistics and natural language processing are harnessed to support the humanities researcher. The processing of large data sets with appropriate software opens up novel and fruitful approaches to questions in the traditional humanities. This report summarizes the Dagstuhl seminar 14301 on “Computational Humanities – bridging the gap between Computer Science and Digital Humanities”
@Article{Biemann:Crane:Fellbaum:Mehler:2014, Author = {Chris Biemann and Gregory R. Crane and Christiane D. Fellbaum and Alexander Mehler}, Title = {Computational Humanities - bridging the gap between Computer Science and Digital Humanities (Dagstuhl Seminar 14301)}, Journal = {Dagstuhl Reports}, Volume = {4}, Number = {7}, Pages = {80-111}, abstract = {Research in the field of Digital Humanities, also known as Humanities Computing, has seen a steady increase over the past years. Situated at the intersection of computing science and the humanities, present efforts focus on making resources such as texts, images, musical pieces and other semiotic artifacts digitally available, searchable and analysable. To this end, computational tools enabling textual search, visual analytics, data mining, statistics and natural language processing are harnessed to support the humanities researcher. The processing of large data sets with appropriate software opens up novel and fruitful approaches to questions in the traditional humanities. This report summarizes the Dagstuhl seminar 14301 on “Computational Humanities – bridging the gap between Computer Science and Digital Humanities”}, issn = {2192-5283}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/dagrep_v004_i007_p080_s14301.pdf}, publisher = {Schloss Dagstuhl--Leibniz-Zentrum für Informatik}, year = 2014 }
-
M. Z. Islam, M. R. Rahman, and A. Mehler, “Readability Classification of Bangla Texts,” in 15th International Conference on Intelligent Text Processing and Computational Linguistics (cicLing), Kathmandu, Nepal, 2014.
[Abstract] [BibTeX]Readability classification is an important application of Natural Language Processing. It aims at judging the quality of documents and to assist writers to identify possible problems. This paper presents a readability classifier for Bangla textbooks using information-theoretic and lexical features. All together 18 features are explored to achieve an F-score of 86.46
@InProceedings{Islam:Rahman:Mehler:2014, Author = {Islam, Md. Zahurul and Rahman, Md. Rashedur and Mehler, Alexander}, Title = {Readability Classification of Bangla Texts}, BookTitle = {15th International Conference on Intelligent Text Processing and Computational Linguistics (cicLing), Kathmandu, Nepal}, abstract = {Readability classification is an important application of Natural Language Processing. It aims at judging the quality of documents and to assist writers to identify possible problems. This paper presents a readability classifier for Bangla textbooks using information-theoretic and lexical features. All together 18 features are explored to achieve an F-score of 86.46}, year = 2014 }
-
A. Mehler, T. vor der Brück, and A. Lücking, “Comparing Hand Gesture Vocabularies for HCI,” in Proceedings of HCI International 2014, 22 – 27 June 2014, Heraklion, Greece, Berlin/New York: Springer, 2014.
[Abstract] [BibTeX]HCI systems are often equipped with gestural interfaces drawing on a predefined set of admitted gestures. We provide an assessment of the fitness of such gesture vocabularies in terms of their learnability and naturalness. This is done by example of rivaling gesture vocabularies of the museum information system WikiNect. In this way, we do not only provide a procedure for evaluating gesture vocabularies, but additionally contribute to design criteria to be followed by the gestures.
@InCollection{Mehler:vor:der:Brueck:Luecking:2014, Author = {Mehler, Alexander and vor der Brück, Tim and Lücking, Andy}, Title = {Comparing Hand Gesture Vocabularies for HCI}, BookTitle = {Proceedings of HCI International 2014, 22 - 27 June 2014, Heraklion, Greece}, Publisher = {Springer}, Address = {Berlin/New York}, abstract = {HCI systems are often equipped with gestural interfaces drawing on a predefined set of admitted gestures. We provide an assessment of the fitness of such gesture vocabularies in terms of their learnability and naturalness. This is done by example of rivaling gesture vocabularies of the museum information system WikiNect. In this way, we do not only provide a procedure for evaluating gesture vocabularies, but additionally contribute to design criteria to be followed by the gestures.}, keywords = {wikinect}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Comparing-Gesture-Vocabularies-1_1.pdf}, website = {{http://link.springer.com/chapter/10.1007/978-3-319-07230-2_8#page-1}}, year = 2014 }
-
A. Mehler, A. Lücking, and G. Abrami, “WikiNect: Image Schemata as a Basis of Gestural Writing for Kinetic Museum Wikis,” Universal Access in the Information Society, pp. 1-17, 2014.
[Abstract] [BibTeX]This paper provides a theoretical assessment of gestures in the context of authoring image-related hypertexts by example of the museum information system WikiNect. To this end, a first implementation of gestural writing based on image schemata is provided (Lakoff in Women, fire, and dangerous things: what categories reveal about the mind. University of Chicago Press, Chicago, 1987). Gestural writing is defined as a sort of coding in which propositions are only expressed by means of gestures. In this respect, it is shown that image schemata allow for bridging between natural language predicates and gestural manifestations. Further, it is demonstrated that gestural writing primarily focuses on the perceptual level of image descriptions (Hollink et al. in Int J Hum Comput Stud 61(5):601–626, 2004). By exploring the metaphorical potential of image schemata, it is finally illustrated how to extend the expressiveness of gestural writing in order to reach the conceptual level of image descriptions. In this context, the paper paves the way for implementing museum information systems like WikiNect as systems of kinetic hypertext authoring based on full-fledged gestural writing.
@Article{Mehler:Luecking:Abrami:2014, Author = {Mehler, Alexander and Lücking, Andy and Abrami, Giuseppe}, Title = {{WikiNect}: Image Schemata as a Basis of Gestural Writing for Kinetic Museum Wikis}, Journal = {Universal Access in the Information Society}, Pages = {1-17}, abstract = {This paper provides a theoretical assessment of gestures in the context of authoring image-related hypertexts by example of the museum information system WikiNect. To this end, a first implementation of gestural writing based on image schemata is provided (Lakoff in Women, fire, and dangerous things: what categories reveal about the mind. University of Chicago Press, Chicago, 1987). Gestural writing is defined as a sort of coding in which propositions are only expressed by means of gestures. In this respect, it is shown that image schemata allow for bridging between natural language predicates and gestural manifestations. Further, it is demonstrated that gestural writing primarily focuses on the perceptual level of image descriptions (Hollink et al. in Int J Hum Comput Stud 61(5):601–626, 2004). By exploring the metaphorical potential of image schemata, it is finally illustrated how to extend the expressiveness of gestural writing in order to reach the conceptual level of image descriptions. In this context, the paper paves the way for implementing museum information systems like WikiNect as systems of kinetic hypertext authoring based on full-fledged gestural writing.}, doi = {10.1007/s10209-014-0386-8}, issn = {1615-5289}, keywords = {wikinect}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/art_10.1007_s10209-014-0386-8.pdf}, website = {http://dx.doi.org/10.1007/s10209-014-0386-8}, year = 2014 }
-
T. vor der Brück, A. Mehler, and M. Z. Islam, “ColLex.EN: Automatically Generating and Evaluating a Full-form Lexicon for English,” in Proceedings of LREC 2014, Reykjavik, Iceland, 2014.
[Abstract] [BibTeX]Currently, a large number of different lexica is available for English. However, substantial and freely available fullform lexica with a high number of named entities are rather rare even in the case of this lingua franca. Existing lexica are often limited in several respects as explained in Section 2. What is missing so far is a freely available substantial machine-readable lexical resource of English that contains a high number of word forms and a large collection of named entities. In this paper, we describe a procedure to generate such a resource by example of English. This lexicon, henceforth called ColLex.EN (for Collecting Lexica for English ), will be made freely available to the public 1. In this paper, we describe how ColLex.EN was collected from existing lexical resources and specify the statistical procedures that we developed to extend and adjust it. No manual modifications were done on the generated word forms and lemmas. Our fully automatic procedure has the advantage that whenever new versions of the source lexica are available, a new version of ColLex.EN can be automatically generated with low effort.
@InProceedings{vor:der:Brueck:Mehler:Islam:2014, Author = {vor der Brück, Tim and Mehler, Alexander and Islam, Md. Zahurul}, Title = {ColLex.EN: Automatically Generating and Evaluating a Full-form Lexicon for English}, BookTitle = {Proceedings of LREC 2014}, Address = {Reykjavik, Iceland}, abstract = {Currently, a large number of different lexica is available for English. However, substantial and freely available fullform lexica with a high number of named entities are rather rare even in the case of this lingua franca. Existing lexica are often limited in several respects as explained in Section 2. What is missing so far is a freely available substantial machine-readable lexical resource of English that contains a high number of word forms and a large collection of named entities. In this paper, we describe a procedure to generate such a resource by example of English. This lexicon, henceforth called ColLex.EN (for Collecting Lexica for English ), will be made freely available to the public 1. In this paper, we describe how ColLex.EN was collected from existing lexical resources and specify the statistical procedures that we developed to extend and adjust it. No manual modifications were done on the generated word forms and lemmas. Our fully automatic procedure has the advantage that whenever new versions of the source lexica are available, a new version of ColLex.EN can be automatically generated with low effort.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/vdbrueck_mehler_islam_collex_lrec.pdf}, website = { http://aclanthology.info/papers/collex-en-automatically-generating-and-evaluating-a-full-form-lexicon-for-english}, year = 2014 }
-
A. Hoenen, “Simulation of Scribal Letter Substitution,” in Analysis of Ancient and Medieval Texts and Manuscripts: Digital Approaches, 2014.
[BibTeX]@InProceedings{Hoenen:2014, Author = {Hoenen, Armin}, Title = {Simulation of Scribal Letter Substitution}, BookTitle = {Analysis of Ancient and Medieval Texts and Manuscripts: Digital Approaches}, Editor = {T.L Andrews and C.Macé}, owner = {hoenen}, website = {http://www.brepols.net/Pages/ShowProduct.aspx?prod_id=IS-9782503552682-1}, year = 2014 }
2013 (20)
-
I. Sejane and S. Eger, “Semantic typologies by means of network analysis of bilingual dictionaries,” in Approaches to Measuring Linguistic Differences, L. Borin and A. Saxena, Eds., De Gruyter, 2013, pp. 447-474.
[BibTeX]@InCollection{Sejane:Eger:2013, Author = {Sejane, Ineta and Eger, Steffen}, Title = {Semantic typologies by means of network analysis of bilingual dictionaries}, BookTitle = {Approaches to Measuring Linguistic Differences}, Publisher = {De Gruyter}, Editor = {Borin, Lars and Saxena, Anju}, Pages = {447-474}, bibtexkey = {eger-sejane_network-typologies2013}, doi = {10.1515/9783110305258.447}, inlg = {English [eng]}, src = {degruyter}, srctrickle = {degruyter#/books/9783110305258/9783110305258.447/9783110305258.447.xml}, url = {http://www.degruyter.com/view/books/9783110305258/9783110305258.447/9783110305258.447.xml}, year = 2013 }
-
S. Eger, “Sequence Segmentation by Enumeration: An Exploration.,” Prague Bull. Math. Linguistics, vol. 100, pp. 113-131, 2013.
[Abstract] [BibTeX]We investigate exhaustive enumeration and subsequent language model evaluation (E&E approach) as an alternative to solving the sequence segmentation problem. We show that, under certain conditions (on string lengths and regarding a possibility to accurately estimate the number of segments), which are satisfied for important NLP applications, such as phonological segmentation, syllabification, and morphological segmentation, the E&E approach is feasible and promises superior results than the standard sequence labeling approach to sequence segmentation.
@Article{Eger:2013:a, Author = {Eger, Steffen}, Title = {Sequence Segmentation by Enumeration: An Exploration.}, Journal = {Prague Bull. Math. Linguistics}, Volume = {100}, Pages = {113-131}, abstract = {We investigate exhaustive enumeration and subsequent language model evaluation (E\&E approach) as an alternative to solving the sequence segmentation problem. We show that, under certain conditions (on string lengths and regarding a possibility to accurately estimate the number of segments), which are satisfied for important NLP applications, such as phonological segmentation, syllabification, and morphological segmentation, the E\&E approach is feasible and promises superior results than the standard sequence labeling approach to sequence segmentation.}, pdf = {http://ufal.mff.cuni.cz/pbml/100/art-eger.pdf}, year = 2013 }
-
S. Eger, “A Contribution to the Theory of Word Length Distribution Based on a Stochastic Word Length Distribution Model.,” Journal of Quantitative Linguistics, vol. 20, iss. 3, pp. 252-265, 2013.
[Abstract] [BibTeX]We derive a stochastic word length distribution model based on the concept of compound distributions and show its relationships with and implications for Wimmer et al. ’s (1994) synergetic word length distribution model.
@Article{Eger:2013:b, Author = {Eger, Steffen}, Title = {A Contribution to the Theory of Word Length Distribution Based on a Stochastic Word Length Distribution Model.}, Journal = {Journal of Quantitative Linguistics}, Volume = {20}, Number = {3}, Pages = {252-265}, abstract = {We derive a stochastic word length distribution model based on the concept of compound distributions and show its relationships with and implications for Wimmer et al. ’s (1994) synergetic word length distribution model.}, year = 2013 }
-
S. Eger, “Sequence alignment with arbitrary steps and further generalizations, with applications to alignments in linguistics.,” Information Sciences, vol. 237, pp. 287-304, 2013.
[Abstract] [BibTeX]We provide simple generalizations of the classical Needleman–Wunsch algorithm for aligning two sequences. First, we let both sequences be defined over arbitrary, potentially different alphabets. Secondly, we consider similarity functions between elements of both sequences with ranges in a semiring. Thirdly, instead of considering only ‘match’, ‘mismatch’ and ‘skip’ operations, we allow arbitrary non-negative alignment ‘steps’ S. Next, we present novel combinatorial formulas for the number of monotone alignments between two sequences for selected steps S. Finally, we illustrate sample applications in natural language processing that require larger steps than available in the original Needleman–Wunsch sequence alignment procedure such that our generalizations can be fruitfully adopted.
@Article{Eger:2013:c, Author = {Eger, Steffen}, Title = {Sequence alignment with arbitrary steps and further generalizations, with applications to alignments in linguistics.}, Journal = {Information Sciences}, Volume = {237}, Pages = {287-304}, abstract = {We provide simple generalizations of the classical Needleman–Wunsch algorithm for aligning two sequences. First, we let both sequences be defined over arbitrary, potentially different alphabets. Secondly, we consider similarity functions between elements of both sequences with ranges in a semiring. Thirdly, instead of considering only ‘match’, ‘mismatch’ and ‘skip’ operations, we allow arbitrary non-negative alignment ‘steps’ S. Next, we present novel combinatorial formulas for the number of monotone alignments between two sequences for selected steps S. Finally, we illustrate sample applications in natural language processing that require larger steps than available in the original Needleman–Wunsch sequence alignment procedure such that our generalizations can be fruitfully adopted.}, website = {http://www.sciencedirect.com/science/article/pii/S0020025513001485}, year = 2013 }
-
S. Eger, “Restricted weighted integer compositions and extended binomial coefficients.,” Journal of Integer Sequences (electronic only), vol. 16, iss. 1, 2013.
[Abstract] [BibTeX]We prove a simple relationship between extended binomial coefficients — natural extensions of the well-known binomial coefficients — and weighted restricted integer compositions. Moreover, wegiveaveryuseful interpretation ofextendedbinomial coefficients as representing distributions of sums of independent discrete random variables. We apply our results, e.g., to determine the distribution of the sum of k logarithmically distributed random variables, and to determining the distribution, specifying all moments, of the random variable whose values are part-products of random restricted integer compositions. Based on our findings and using the central limit theorem, we also give generalized Stirling formulae for central extended binomial coefficients. We enlarge the list of known properties of extended binomial coefficients.
@Article{Eger:2013:d, Author = {Eger, Steffen}, Title = {Restricted weighted integer compositions and extended binomial coefficients.}, Journal = {Journal of Integer Sequences (electronic only)}, Volume = {16}, Number = {1}, abstract = {We prove a simple relationship between extended binomial coefficients — natural extensions of the well-known binomial coefficients — and weighted restricted integer compositions. Moreover, wegiveaveryuseful interpretation ofextendedbinomial coefficients as representing distributions of sums of independent discrete random variables. We apply our results, e.g., to determine the distribution of the sum of k logarithmically distributed random variables, and to determining the distribution, specifying all moments, of the random variable whose values are part-products of random restricted integer compositions. Based on our findings and using the central limit theorem, we also give generalized Stirling formulae for central extended binomial coefficients. We enlarge the list of known properties of extended binomial coefficients.}, issn = {1530-7638}, pdf = {https://cs.uwaterloo.ca/journals/JIS/VOL16/Eger/eger6.pdf}, publisher = {School of Computer Science, University of Waterloo, Waterloo, ON}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.397.3745}, year = 2013 }
-
A. Mehler, R. Schneider, and A. Storrer, Webkorpora in Computerlinguistik und Sprachforschung, R. Schneider, A. Storrer, and A. Mehler, Eds., JLCL, 2013, vol. 28.
[BibTeX]@Book{Schneider:Storrer:Mehler:2013, Author = {Mehler, Alexander and Schneider, Roman and Storrer, Angelika}, Editor = {Roman Schneider and Angelika Storrer and Alexander Mehler}, Title = {Webkorpora in Computerlinguistik und Sprachforschung}, Publisher = {JLCL}, Volume = {28}, Number = {2}, Series = {Journal for Language Technology and Computational Linguistics (JLCL)}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/Webkorpora-300-20.png}, issn = {2190-6858}, pagetotal = {107}, pdf = {http://www.jlcl.org/2013_Heft2/H2013-2.pdf}, year = 2013 }
-
A. Mehler, A. Lücking, T. vor der Brück, and G. Abrami, WikiNect – A Kinetic Artwork Wiki for Exhibition Visitors, 2013.
[Poster][BibTeX]@Misc{Mehler:Luecking:vor:der:Brueck:2013:a, Author = {Mehler, Alexander and Lücking, Andy and vor der Brück, Tim and Abrami, Giuseppe}, Title = {WikiNect - A Kinetic Artwork Wiki for Exhibition Visitors}, HowPublished = {Poster Presentation at the Scientific Computing and Cultural Heritage 2013 Conference, Heidelberg}, keywords = {wikinect}, month = {11}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/SCCHPoster2013.pdf}, url = {http://scch2013.wordpress.com/}, year = 2013 }
-
A. Lücking, Theoretische Bausteine für einen semiotischen Ansatz zum Einsatz von Gestik in der Aphasietherapie, 2013.
[BibTeX]@Misc{Luecking:2013:c, Author = {Lücking, Andy}, Title = {Theoretische Bausteine für einen semiotischen Ansatz zum Einsatz von Gestik in der Aphasietherapie}, HowPublished = {Talk at the BKL workshop 2013, Bochum}, month = {05}, url = {http://www.bkl-ev.de/bkl_workshop/archiv/workshop13_programm.php}, year = 2013 }
-
A. Lücking, Eclectic Semantics for Non-Verbal Signs, 2013.
[BibTeX]@Misc{Luecking:2013:d, Author = {Lücking, Andy}, Title = {Eclectic Semantics for Non-Verbal Signs}, HowPublished = {Talk at the Conference on Investigating semantics: Empirical and philosophical approaches, Bochum}, month = {10}, url = {http://www.ruhr-uni-bochum.de/phil-lang/investigating/index.html}, year = 2013 }
-
A. Lücking, “Multimodal Propositions? From Semiotic to Semantic Considerations in the Case of Gestural Deictics,” in Poster Abstracts of the Proceedings of the 17th Workshop on the Semantics and Pragmatics of Dialogue, Amsterdam, 2013, pp. 221-223.
[Poster][BibTeX]@InProceedings{Luecking:2013:e, Author = {Lücking, Andy}, Title = {Multimodal Propositions? From Semiotic to Semantic Considerations in the Case of Gestural Deictics}, BookTitle = {Poster Abstracts of the Proceedings of the 17th Workshop on the Semantics and Pragmatics of Dialogue}, Editor = {Fernandez, Raquel and Isard, Amy}, Series = {SemDial 2013}, Pages = {221-223}, Address = {Amsterdam}, month = {12}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/dialdam2013.pdf}, year = 2013 }
-
M. Z. Islam and A. Hoenen, “Source and Translation Classifiction using Most Frequent Words,” in Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP), 2013.
[Abstract] [BibTeX]Recently, translation scholars have made some general claims about translation properties. Some of these are source language independent while others are not. Koppel and Ordan (2011) performed empirical studies to validate both types of properties using English source texts and other texts translated into English. Obviously, corpora of this sort, which focus on a single language, are not adequate for claiming universality of translation prop- erties. In this paper, we are validating both types of translation properties using original and translated texts from six European languages.
@InProceedings{Islam:Hoenen:2013, Author = {Islam, Md. Zahurul and Hoenen, Armin}, Title = {Source and Translation Classifiction using Most Frequent Words}, BookTitle = {Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP)}, abstract = {Recently, translation scholars have made some general claims about translation properties. Some of these are source language independent while others are not. Koppel and Ordan (2011) performed empirical studies to validate both types of properties using English source texts and other texts translated into English. Obviously, corpora of this sort, which focus on a single language, are not adequate for claiming universality of translation prop- erties. In this paper, we are validating both types of translation properties using original and translated texts from six European languages.}, pdf = {http://www.aclweb.org/anthology/I/I13/I13-1185.pdf}, website = {http://aclanthology.info/papers/source-and-translation-classification-using-most-frequent-words}, year = 2013 }
-
A. Lücking and A. Mehler, “On Three Notions of Grounding of Artificial Dialog Companions,” Science, Technology & Innovation Studies, vol. 10, iss. 1, pp. 31-36, 2013.
[Abstract] [BibTeX]We provide a new, theoretically motivated evaluation grid for assessing the conversational achievements of Artificial Dialog Companions (ADCs). The grid is spanned along three grounding problems. Firstly, it is argued that symbol grounding in general has to be instrinsic. Current approaches in this context, however, are limited to a certain kind of expression that can be grounded in this way. Secondly, we identify three requirements for conversational grounding, the process leading to mutual understanding. Finally, we sketch a test case for symbol grounding in the form of the philosophical grounding problem that involves the use of modal language. Together, the three grounding problems provide a grid that allows us to assess ADCs’ dialogical performances and to pinpoint future developments on these grounds.
@Article{Luecking:Mehler:2013:a, Author = {Lücking, Andy and Mehler, Alexander}, Title = {On Three Notions of Grounding of Artificial Dialog Companions}, Journal = {Science, Technology \& Innovation Studies}, Volume = {10}, Number = {1}, Pages = {31-36}, abstract = {We provide a new, theoretically motivated evaluation grid for assessing the conversational achievements of Artificial Dialog Companions (ADCs). The grid is spanned along three grounding problems. Firstly, it is argued that symbol grounding in general has to be instrinsic. Current approaches in this context, however, are limited to a certain kind of expression that can be grounded in this way. Secondly, we identify three requirements for conversational grounding, the process leading to mutual understanding. Finally, we sketch a test case for symbol grounding in the form of the philosophical grounding problem that involves the use of modal language. Together, the three grounding problems provide a grid that allows us to assess ADCs’ dialogical performances and to pinpoint future developments on these grounds.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/STI-final-badge.pdf}, website = {http://www.sti-studies.de/ojs/index.php/sti/article/view/143}, year = 2013 }
-
Die Dynamik sozialer und sprachlicher Netzwerke: Konzepte, Methoden und empirische Untersuchungen an Beispielen des WWW, B. Frank-Job, A. Mehler, and T. Sutter, Eds., Wiesbaden: Springer VS, 2013.
[Abstract] [BibTeX]In diesem Band präsentieren Medien- und Informationswissenschaftler, Netzwerkforscher aus Informatik, Texttechnologie und Physik, Soziologen und Linguisten interdisziplinär Aspekte der Erforschung komplexer Mehrebenen-Netzwerke. Im Zentrum ihres Interesses stehen Untersuchungen zum Zusammenhang zwischen sozialen und sprachlichen Netzwerken und ihrer Dynamiken, aufgezeigt an empirischen Beispielen aus dem Bereich des Web 2.0, aber auch an historischen Dokumentenkorpora sowie an Rezeptions-Netzwerken aus Kunst- und Literaturwissenschaft.
@Book{FrankJob:Mehler:Sutter:2013, Editor = {Barbara Frank-Job and Alexander Mehler and Tilmann Sutter}, Title = {Die Dynamik sozialer und sprachlicher Netzwerke: Konzepte, Methoden und empirische Untersuchungen an Beispielen des WWW}, Publisher = {Springer VS}, Address = {Wiesbaden}, abstract = {In diesem Band pr{\"a}sentieren Medien- und Informationswissenschaftler, Netzwerkforscher aus Informatik, Texttechnologie und Physik, Soziologen und Linguisten interdisziplin{\"a}r Aspekte der Erforschung komplexer Mehrebenen-Netzwerke. Im Zentrum ihres Interesses stehen Untersuchungen zum Zusammenhang zwischen sozialen und sprachlichen Netzwerken und ihrer Dynamiken, aufgezeigt an empirischen Beispielen aus dem Bereich des Web 2.0, aber auch an historischen Dokumentenkorpora sowie an Rezeptions-Netzwerken aus Kunst- und Literaturwissenschaft.}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/DieDynamikSozialerUndSprachlicherNetzwerke.jpg}, pagetotal = {240}, year = 2013 }
-
A. Lücking, “Interfacing Speech and Co-Verbal Gesture: Exemplification,” in Proceedings of the 35th Annual Conference of the German Linguistic Society, Potsdam, Germany, 2013, pp. 284-286.
[BibTeX]@InProceedings{Luecking:2013:b, Author = {Lücking, Andy}, Title = {Interfacing Speech and Co-Verbal Gesture: Exemplification}, BookTitle = {Proceedings of the 35th Annual Conference of the German Linguistic Society}, Series = {DGfS 2013}, Pages = {284-286}, Address = {Potsdam, Germany}, year = 2013 }
-
A. Lücking, Ikonische Gesten. Grundzüge einer linguistischen Theorie, Berlin and Boston: De Gruyter, 2013. Zugl. Diss. Univ. Bielefeld (2011)
[Abstract] [BibTeX]Nicht-verbale Zeichen, insbesondere sprachbegleitende Gesten, spielen eine herausragende Rolle in der menschlichen Kommunikation. Um eine Analyse von Gestik innerhalb derjenigen Disziplinen, die sich mit der Erforschung und Modellierung von Dialogen beschäftigen, zu ermöglichen, bedarf es einer entsprechenden linguistischen Rahmentheorie. „Ikonische Gesten“ bietet einen ersten zeichen- und wahrnehmungstheoretisch motivierten Rahmen an, in dem eine grammatische Analyse der Integration von Sprache und Gestik möglich ist. Ausgehend von einem Abriss semiotischer Zugänge zu ikonischen Zeichen wird der vorherrschende Ähnlichkeitsansatz unter Rückgriff auf Wahrnehmungstheorien zugunsten eines Exemplifikationsansatzes verworfen. Exemplifikation wird im Rahmen einer unifikationsbasierten Grammatik umgesetzt. Dort werden u.a. multimodale Wohlgeformtheit, Synchronie und multimodale Subkategorisierung als neue Gegenstände linguistischer Forschung eingeführt und im Rahmen einer integrativen Analyse von Sprache und Gestik modelliert.
@Book{Luecking:2013, Author = {Lücking, Andy}, Title = {Ikonische Gesten. Grundzüge einer linguistischen Theorie}, Publisher = {De Gruyter}, Address = {Berlin and Boston}, Note = {Zugl. Diss. Univ. Bielefeld (2011)}, abstract = {Nicht-verbale Zeichen, insbesondere sprachbegleitende Gesten, spielen eine herausragende Rolle in der menschlichen Kommunikation. Um eine Analyse von Gestik innerhalb derjenigen Disziplinen, die sich mit der Erforschung und Modellierung von Dialogen besch{\"a}ftigen, zu ermöglichen, bedarf es einer entsprechenden linguistischen Rahmentheorie. „Ikonische Gesten“ bietet einen ersten zeichen- und wahrnehmungstheoretisch motivierten Rahmen an, in dem eine grammatische Analyse der Integration von Sprache und Gestik möglich ist. Ausgehend von einem Abriss semiotischer Zug{\"a}nge zu ikonischen Zeichen wird der vorherrschende {\"A}hnlichkeitsansatz unter Rückgriff auf Wahrnehmungstheorien zugunsten eines Exemplifikationsansatzes verworfen. Exemplifikation wird im Rahmen einer unifikationsbasierten Grammatik umgesetzt. Dort werden u.a. multimodale Wohlgeformtheit, Synchronie und multimodale Subkategorisierung als neue Gegenst{\"a}nde linguistischer Forschung eingeführt und im Rahmen einer integrativen Analyse von Sprache und Gestik modelliert.}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/ikonischeGesten.jpg}, year = 2013 }
-
M. Z. Islam and A. Mehler, “Automatic Readability Classification of Crowd-Sourced Data based on Linguistic and Information-Theoretic Features,” in 14th International Conference on Intelligent Text Processing and Computational Linguistics, 2013.
[Abstract] [BibTeX]This paper presents a classifier of text readability based on information-theoretic features. The classifier was developed based on a linguistic approach to readability that explores lexical, syntactic and semantic features. For this evaluation we extracted a corpus of 645 articles from Wikipedia together with their quality judgments. We show that information-theoretic features perform as well as their linguistic counterparts even if we explore several linguistic levels at once.
@InProceedings{Islam:Mehler:2013:a, Author = {Islam, Md. Zahurul and Mehler, Alexander}, Title = {Automatic Readability Classification of Crowd-Sourced Data based on Linguistic and Information-Theoretic Features}, BookTitle = {14th International Conference on Intelligent Text Processing and Computational Linguistics}, abstract = {This paper presents a classifier of text readability based on information-theoretic features. The classifier was developed based on a linguistic approach to readability that explores lexical, syntactic and semantic features. For this evaluation we extracted a corpus of 645 articles from Wikipedia together with their quality judgments. We show that information-theoretic features perform as well as their linguistic counterparts even if we explore several linguistic levels at once.}, owner = {zahurul}, pdf = {http://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/download/1516/1497}, timestamp = {2013.01.22}, website = {http://www.redalyc.org/articulo.oa?id=61527437002}, year = 2013 }
-
M. Z. Islam and R. Rahman, “English to Bangla Name Transliteration System (Abstract),” in The 23rd Meeting of Computational Linguistics in the Netherlands (CLIN 2013), 2013.
[Abstract] [BibTeX]Machine translation systems always struggle transliterating names and unknown words during the translation process. It becomes more problematic when the source and the target language use different scripts for writing. To handle this problem, transliteration systems are becoming popular as additional modules of the MT systems. In this abstract, we are presenting an English to Bangla name transliteration system that outperforms Google’s transliteration system. The transliteration system is the same as the phrase based statistical machine translation system, but it works on character level rather than on phrase level. The performance of a statistical system is directly correlated with the size of the training corpus. In this work, 2200 names are extracted from the Wikipedia cross lingual links and from Geonames . Also 3694 names are manually transliterated and added to the data. 4716 names are used for training, 590 for tuning and 588 names are used for testing. If we consider only the candidate transliterations, the system gives 64.28% accuracy. The performance increases to more than 90%, if we consider only the top 5 transliterations. To compare with the Google’s English to Bangla transliteration system, a list of 100 names are randomly selected from the test data and translated by both systems. Our system gives 63% accuracy where the Google’s transliteration system does not transliterate a single name correctly. We have found significant improvement in terms of BLUE and TER score when we add the transliteration module with an English to Bangla machine transliteration system.
@InProceedings{Islam:Rahman:2013, Author = {Islam, Md. Zahurul and Rahman, Rashedur}, Title = {English to Bangla Name Transliteration System (Abstract)}, BookTitle = {The 23rd Meeting of Computational Linguistics in the Netherlands (CLIN 2013)}, abstract = {Machine translation systems always struggle transliterating names and unknown words during the translation process. It becomes more problematic when the source and the target language use different scripts for writing. To handle this problem, transliteration systems are becoming popular as additional modules of the MT systems. In this abstract, we are presenting an English to Bangla name transliteration system that outperforms Google’s transliteration system. The transliteration system is the same as the phrase based statistical machine translation system, but it works on character level rather than on phrase level. The performance of a statistical system is directly correlated with the size of the training corpus. In this work, 2200 names are extracted from the Wikipedia cross lingual links and from Geonames . Also 3694 names are manually transliterated and added to the data. 4716 names are used for training, 590 for tuning and 588 names are used for testing. If we consider only the candidate transliterations, the system gives 64.28% accuracy. The performance increases to more than 90%, if we consider only the top 5 transliterations. To compare with the Google’s English to Bangla transliteration system, a list of 100 names are randomly selected from the test data and translated by both systems. Our system gives 63% accuracy where the Google’s transliteration system does not transliterate a single name correctly. We have found significant improvement in terms of BLUE and TER score when we add the transliteration module with an English to Bangla machine transliteration system.}, owner = {zahurul}, timestamp = {2013.01.22}, website = {https://www.academia.edu/3955036/English_to_Bangla_Name_Transliteration_System}, year = 2013 }
-
A. Mehler, C. Stegbauer, and R. Gleim, “Zur Struktur und Dynamik der kollaborativen Plagiatsdokumentation am Beispiel des GuttenPlag Wiki: eine Vorstudie,” in Die Dynamik sozialer und sprachlicher Netzwerke. Konzepte, Methoden und empirische Untersuchungen am Beispiel des WWW, B. Frank-Job, A. Mehler, and T. Sutter, Eds., Wiesbaden: VS Verlag, 2013.
[BibTeX]@InCollection{Mehler:Stegbauer:Gleim:2013, Author = {Mehler, Alexander and Stegbauer, Christian and Gleim, Rüdiger}, Title = {Zur Struktur und Dynamik der kollaborativen Plagiatsdokumentation am Beispiel des GuttenPlag Wiki: eine Vorstudie}, BookTitle = {Die Dynamik sozialer und sprachlicher Netzwerke. Konzepte, Methoden und empirische Untersuchungen am Beispiel des WWW}, Publisher = {VS Verlag}, Editor = {Frank-Job, Barbara and Mehler, Alexander and Sutter, Tilman}, Address = {Wiesbaden}, year = 2013 }
-
A. Lücking, K. Bergman, F. Hahn, S. Kopp, and H. Rieser, “Data-based Analysis of Speech and Gesture: The Bielefeld Speech and Gesture Alignment Corpus (SaGA) and its Applications,” Journal of Multimodal User Interfaces, vol. 7, iss. 1-2, pp. 5-18, 2013.
[Abstract] [BibTeX]Communicating face-to-face, interlocutors frequently produce multimodal meaning packages consisting of speech and accompanying gestures. We discuss a systematically annotated speech and gesture corpus consisting of 25 route-and-landmark-description dialogues, the Bielefeld Speech and Gesture Alignment corpus (SaGA), collected in experimental face-to-face settings. We first describe the primary and secondary data of the corpus and its reliability assessment. Then we go into some of the projects carried out using SaGA demonstrating the wide range of its usability: on the empirical side, there is work on gesture typology, individual and contextual parameters influencing gesture production and gestures’ functions for dialogue structure. Speech-gesture interfaces have been established extending unification-based grammars. In addition, the development of a computational model of speech-gesture alignment and its implementation constitutes a research line we focus on.
@Article{Luecking:Bergmann:Hahn:Kopp:Rieser:2012, Author = {Lücking, Andy and Bergman, Kirsten and Hahn, Florian and Kopp, Stefan and Rieser, Hannes}, Title = {Data-based Analysis of Speech and Gesture: The Bielefeld Speech and Gesture Alignment Corpus (SaGA) and its Applications}, Journal = {Journal of Multimodal User Interfaces}, Volume = {7}, Number = {1-2}, Pages = {5-18}, abstract = {Communicating face-to-face, interlocutors frequently produce multimodal meaning packages consisting of speech and accompanying gestures. We discuss a systematically annotated speech and gesture corpus consisting of 25 route-and-landmark-description dialogues, the Bielefeld Speech and Gesture Alignment corpus (SaGA), collected in experimental face-to-face settings. We first describe the primary and secondary data of the corpus and its reliability assessment. Then we go into some of the projects carried out using SaGA demonstrating the wide range of its usability: on the empirical side, there is work on gesture typology, individual and contextual parameters influencing gesture production and gestures’ functions for dialogue structure. Speech-gesture interfaces have been established extending unification-based grammars. In addition, the development of a computational model of speech-gesture alignment and its implementation constitutes a research line we focus on.}, doi = {10.1007/s12193-012-0106-8}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/MMUI-SaGA-revision2.pdf}, website = {http://www.springerlink.com/content/a547448u86h3116x/?MUD=MP}, year = 2013 }
-
N. Beckage, M. S. Vitevitch, A. Mehler, and E. Colunga, “Using Complex Network Analysis in the Cognitive Sciences,” in Proceedings of the 35th Annual Meeting of the Cognitive Science Society, CogSci 2013, Berlin, Germany, July 31 – August 3, 2013, 2013.
[BibTeX]@InProceedings{Beckage:et:al:2013, Author = {Nicole Beckage and Michael S. Vitevitch and Alexander Mehler and Eliana Colunga}, Title = {Using Complex Network Analysis in the Cognitive Sciences}, BookTitle = {Proceedings of the 35th Annual Meeting of the Cognitive Science Society, CogSci 2013, Berlin, Germany, July 31 - August 3, 2013}, Editor = {Markus Knauff and Michael Pauen and Natalie Sebanz and Ipke Wachsmuth}, Publisher = {cognitivesciencesociety.org}, year = 2013 }
2012 (26)
-
A. Mehler and L. Romary, Handbook of Technical Communication, Berlin: De Gruyter Mouton, 2012.
[BibTeX]@Book{Mehler:Romary:2012, Author = {Mehler, Alexander and Romary, Laurent}, Title = {Handbook of Technical Communication}, Publisher = {De Gruyter Mouton}, Address = {Berlin}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/HandbookTechnicalCommunication.jpg}, pagetotal = {839}, year = 2012 }
-
O. Abramov, “Network theory applied to linguistics: new advances in language classification and typology,” PhD Thesis, 2012.
[Abstract] [BibTeX]This thesis bridges between two scientific fields -- linguistics and computer science -- in terms of Linguistic Networks. From the linguistic point of view we examine whether languages can be distinguished when looking at network topology of different linguistic networks. We deal with up to 17 languages and ask how far the methods of network theory reveal the peculiarities of single languages. We present and apply network models from different levels of linguistic representation: syntactic, phonological and morphological. The network models presented here allow to integrate various linguistic features at once, which enables a more abstract, holistic view at the particular language. From the point of view of computer science we elaborate the instrumentarium of network theory applying it to a new field. We study the expressiveness of different network features and their ability to characterize language structure. We evaluate the interplay of these features and their goodness in the task of classifying languages genealogically. Among others we compare network features related to: average degree, average geodesic distance, clustering, entropy-based indices, assortativity, centrality, compactness etc. We also propose some new indices that can serve as additional characteristics of networks. The results obtained show that network models succeed in classifying related languages, and allow to study language structure in general. The mathematical analysis of the particular network indices brings new insights into the nature of these indices and their potential when applied to different networks.
@PhdThesis{Abramov:2012, Author = {Abramov, Olga}, Title = {Network theory applied to linguistics: new advances in language classification and typology}, School = {Bielefeld University, Germany}, abstract = {This thesis bridges between two scientific fields -- linguistics and computer science -- in terms of Linguistic Networks. From the linguistic point of view we examine whether languages can be distinguished when looking at network topology of different linguistic networks. We deal with up to 17 languages and ask how far the methods of network theory reveal the peculiarities of single languages. We present and apply network models from different levels of linguistic representation: syntactic, phonological and morphological. The network models presented here allow to integrate various linguistic features at once, which enables a more abstract, holistic view at the particular language. From the point of view of computer science we elaborate the instrumentarium of network theory applying it to a new field. We study the expressiveness of different network features and their ability to characterize language structure. We evaluate the interplay of these features and their goodness in the task of classifying languages genealogically. Among others we compare network features related to: average degree, average geodesic distance, clustering, entropy-based indices, assortativity, centrality, compactness etc. We also propose some new indices that can serve as additional characteristics of networks. The results obtained show that network models succeed in classifying related languages, and allow to study language structure in general. The mathematical analysis of the particular network indices brings new insights into the nature of these indices and their potential when applied to different networks.}, pdf = {https://pub.uni-bielefeld.de/download/2538828/2542368}, website = {http://pub.uni-bielefeld.de/publication/2538828}, year = 2012 }
-
A. Hoenen, “Measuring Repetitiveness in Texts, a Preliminary Investigation,” Sprache und Datenverarbeitung. International Journal for Language Data Processing, vol. 36, iss. 2, pp. 93-104, 2012.
[Abstract] [BibTeX]In this paper, a model is presented for the automatic measurement that can systematically describe the usage and function of the phenomenon of repetition in written text. The motivating hypothesis for this study is that the more repetitive a text is, the easier it is to memorize. Therefore, an automated measurement index can provide feedback to writers and for those who design texts that are often memorized including songs, holy texts, theatrical plays, and advertising slogans. The potential benefits of this kind of systematic feedback are numerous, the main one being that content creators would be able to employ a standard threshold of memorizability. This study explores multiple ways of implementing and calculating repetitiveness across levels of analysis (such as paragraph-level or sub-word level) genres (such as songs, holy texts, and other genres) and languages, integrating these into the a model for the automatic measurement of repetitiveness. The Avestan language and some of its idiosyncratic features are explored in order to illuminate how the proposed index is applied in the ranking of texts according to their repetitiveness.
@Article{Hoenen:2012:a, Author = {Hoenen, Armin}, Title = {Measuring Repetitiveness in Texts, a Preliminary Investigation}, Journal = {Sprache und Datenverarbeitung. International Journal for Language Data Processing}, Volume = {36}, Number = {2}, Pages = {93-104}, abstract = {In this paper, a model is presented for the automatic measurement that can systematically describe the usage and function of the phenomenon of repetition in written text. The motivating hypothesis for this study is that the more repetitive a text is, the easier it is to memorize. Therefore, an automated measurement index can provide feedback to writers and for those who design texts that are often memorized including songs, holy texts, theatrical plays, and advertising slogans. The potential benefits of this kind of systematic feedback are numerous, the main one being that content creators would be able to employ a standard threshold of memorizability. This study explores multiple ways of implementing and calculating repetitiveness across levels of analysis (such as paragraph-level or sub-word level) genres (such as songs, holy texts, and other genres) and languages, integrating these into the a model for the automatic measurement of repetitiveness. The Avestan language and some of its idiosyncratic features are explored in order to illuminate how the proposed index is applied in the ranking of texts according to their repetitiveness.}, website = {http://www.linse.uni-due.de/jahrgang-36-2012/articles/measuring-repetitiveness-in-texts-a-preliminary-investigation.html}, year = 2012 }
-
S. Eger, “The Combinatorics of String Alignments: Reconsidering the Problem.,” Journal of Quantitative Linguistics, vol. 19, iss. 1, pp. 32-53, 2012.
[Abstract] [BibTeX]In recent work, Covington discusses the number of alignments of two strings. Thereby, Covington defines an alignment as “a way of pairing up elements of two strings, optionally skipping some but preserving the order”. This definition has drawbacks as it excludes many relevant situations. In this work, we specify the notion of an alignment so that many linguistically interesting situations are covered. To this end, we define an alignment in an abstract manner as a set of pairs and then define three properties on such sets. Secondly, we specify the numbers of possibilities of aligning two strings in each case.
@Article{Eger:2012:a, Author = {Eger, Steffen}, Title = {The Combinatorics of String Alignments: Reconsidering the Problem.}, Journal = {Journal of Quantitative Linguistics}, Volume = {19}, Number = {1}, Pages = {32-53}, abstract = {In recent work, Covington discusses the number of alignments of two strings. Thereby, Covington defines an alignment as “a way of pairing up elements of two strings, optionally skipping some but preserving the order”. This definition has drawbacks as it excludes many relevant situations. In this work, we specify the notion of an alignment so that many linguistically interesting situations are covered. To this end, we define an alignment in an abstract manner as a set of pairs and then define three properties on such sets. Secondly, we specify the numbers of possibilities of aligning two strings in each case.}, website = { http://www.tandfonline.com/doi/full/10.1080/09296174.2011.638792#tabModule}, year = 2012 }
-
S. Eger, “S-Restricted Monotone Alignments: Algorithm, Search Space, and Applications,” in Proceedings of COLING 2012, Mumbai, India, 2012, pp. 781-798.
[Abstract] [BibTeX]We present a simple and straightforward alignment algorithm for monotone many-to-many alignments in grapheme-to-phoneme conversion and related fields such as morphology, and discuss a few noteworthy extensions. Moreover, we specify combinatorial formulas for monotone many-to-many alignments and decoding in G2P which indicate that exhaustive enumeration is generally possible, so that some limitations of our approach can easily be overcome. Finally, we present a decoding scheme, within the monotone many-to-many alignment paradigm, that relates the decoding problem to restricted integer compositions and that is, putatively, superior to alternatives suggested in the literatur
@InProceedings{Eger:2012:b, Author = {Eger, Steffen}, Title = {S-Restricted Monotone Alignments: Algorithm, Search Space, and Applications}, BookTitle = {Proceedings of COLING 2012}, Pages = {781-798}, Address = {Mumbai, India}, Publisher = {The COLING 2012 Organizing Committee}, abstract = {We present a simple and straightforward alignment algorithm for monotone many-to-many alignments in grapheme-to-phoneme conversion and related fields such as morphology, and discuss a few noteworthy extensions. Moreover, we specify combinatorial formulas for monotone many-to-many alignments and decoding in G2P which indicate that exhaustive enumeration is generally possible, so that some limitations of our approach can easily be overcome. Finally, we present a decoding scheme, within the monotone many-to-many alignment paradigm, that relates the decoding problem to restricted integer compositions and that is, putatively, superior to alternatives suggested in the literatur}, pdf = {http://aclweb.org/anthology/C/C12/C12-1048.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.5941}, year = 2012 }
-
S. Eger, “Lexical semantic typologies from bilingual corpora – A framework,” in SEM 2012: The First Joint Conference on Lexical and Computational Semantics — Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), Montreal, Canada, 2012, pp. 90-94.
[Abstract] [BibTeX]We present a framework, based on Sejane and Eger (2012), for inducing lexical semantic typologies for groups of languages. Our framework rests on lexical semantic association networks derived from encoding, via bilingual corpora, each language in a common reference language, the tertium comparationis, so that distances between languages can easily be determined.
@InProceedings{Eger:2012:c, Author = {Eger, Steffen}, Title = {Lexical semantic typologies from bilingual corpora - A framework}, BookTitle = {SEM 2012: The First Joint Conference on Lexical and Computational Semantics -- Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)}, Pages = {90-94}, Address = {Montreal, Canada}, Publisher = {Association for Computational Linguistics}, abstract = {We present a framework, based on Sejane and Eger (2012), for inducing lexical semantic typologies for groups of languages. Our framework rests on lexical semantic association networks derived from encoding, via bilingual corpora, each language in a common reference language, the tertium comparationis, so that distances between languages can easily be determined.}, pdf = {http://www.aclweb.org/anthology/S12-1015}, website = {http://dl.acm.org/citation.cfm?id=2387653}, year = 2012 }
-
A. Mehler, C. Stegbauer, and R. Gleim, “Latent Barriers in Wiki-based Collaborative Writing,” in Proceedings of the Wikipedia Academy: Research and Free Knowledge. June 29 – July 1 2012, Berlin, 2012.
[BibTeX]@InProceedings{Mehler:Stegbauer:Gleim:2012:b, Author = {Mehler, Alexander and Stegbauer, Christian and Gleim, Rüdiger}, Title = {Latent Barriers in Wiki-based Collaborative Writing}, BookTitle = {Proceedings of the Wikipedia Academy: Research and Free Knowledge. June 29 - July 1 2012}, Address = {Berlin}, month = {July}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/12_Paper_Alexander_Mehler_Christian_Stegbauer_Ruediger_Gleim.pdf}, year = 2012 }
-
A. Hoenen and T. Jügel, Altüberlieferte Sprachen als Gegenstand der Texttechnologie — Ancient Languages as the Object of Text Technology, A. Hoenen and T. Jügel, Eds., JLCL, 2012, vol. 27.
[Abstract] [BibTeX]‘Avestan’ is the name of the ritual language of Zor oastrianism, which was the state religion of the Iranian empire in Achaemenid, Arsacid and Sasanid times, covering a time span of more than 1200 years. [1] It is named after the ‘Avesta’, i.e., the collection of holy scriptures that form the basis of the religion which was allegedly founded by Zarathushtra, also known as Zoroaster, by about the beginning of the first millennium B.C. Together with Vedic Sanskrit, Avestan represents one of the most archaic witnesses of the Indo-Iranian branch of the Indo-European languages, which makes it especially interesting for historical-comparative linguistics. This is why the texts of the Avesta were among the first objects of electronic corpus building that were undertaken in the framework of Indo-European studies, leading to the establishment of the TITUS database (‘Thesaurus indogermanischer Text- u nd Sprachmaterialien’). [2] Today, the complete Avestan corpus is available, together with elaborate search functions [3] and an extended version of the subcorpus of the so-called ‘Yasna’, which covers a great deal of the attestation of variant readings. [4] Right from the beginning of their computational work concerning the Avesta, the compilers [5] had to cope with the fact that the texts contained in it have been transmitted in a special script written from right to left, which was also used for printing them in the scholarly editions used until today. [6] It goes without saying that there was no way in the middle of the 1980s to encode the Avestan scriptures exactly as they are found in the manuscripts. Instead, we had to rely upon transcriptional devices that were dictated by the restrictions of character encoding as provided by the computer systems used. As the problems we had to face in this respect and the solutions we could apply are typical for the development of computational work on ancient languages, it seems worthwhile to sketch them out here.
@Book{Hoenen:Jügel:2012, Author = {Hoenen, Armin and Jügel, Thomas}, Editor = {Armin Hoenen and Thomas Jügel}, Title = {Altüberlieferte Sprachen als Gegenstand der Texttechnologie -- Ancient Languages as the Object of Text Technology}, Publisher = {JLCL}, Volume = {27}, Number = {2}, abstract = {‘Avestan’ is the name of the ritual language of Zor oastrianism, which was the state religion of the Iranian empire in Achaemenid, Arsacid and Sasanid times, covering a time span of more than 1200 years. [1] It is named after the ‘Avesta’, i.e., the collection of holy scriptures that form the basis of the religion which was allegedly founded by Zarathushtra, also known as Zoroaster, by about the beginning of the first millennium B.C. Together with Vedic Sanskrit, Avestan represents one of the most archaic witnesses of the Indo-Iranian branch of the Indo-European languages, which makes it especially interesting for historical-comparative linguistics. This is why the texts of the Avesta were among the first objects of electronic corpus building that were undertaken in the framework of Indo-European studies, leading to the establishment of the TITUS database (‘Thesaurus indogermanischer Text- u nd Sprachmaterialien’). [2] Today, the complete Avestan corpus is available, together with elaborate search functions [3] and an extended version of the subcorpus of the so-called ‘Yasna’, which covers a great deal of the attestation of variant readings. [4] Right from the beginning of their computational work concerning the Avesta, the compilers [5] had to cope with the fact that the texts contained in it have been transmitted in a special script written from right to left, which was also used for printing them in the scholarly editions used until today. [6] It goes without saying that there was no way in the middle of the 1980s to encode the Avestan scriptures exactly as they are found in the manuscripts. Instead, we had to rely upon transcriptional devices that were dictated by the restrictions of character encoding as provided by the computer systems used. As the problems we had to face in this respect and the solutions we could apply are typical for the development of computational work on ancient languages, it seems worthwhile to sketch them out here.}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/AltueberlieferteSprachen-300-20.png}, issn = {2190-6858}, pdf = {http://www.jlcl.org/2012_Heft2/H2012-2.pdf}, year = 2012 }
-
T. vor der Brück, Wissensakquisition mithilfe maschineller Lernverfahren auf tiefen semantischen Repräsentationen, Heidelberg, Germany: Springer, 2012.
[Abstract] [BibTeX]Eine große Wissensbasis ist eine Voraussetzung für eine Vielzahl von Anwendungen im Bereich der automatischen Sprachverarbeitung, wie Frage-Antwort- oder Information-Retrieval-Systeme. Ein Mensch hat sich das erforderliche Wissen, um Informationen zu suchen oder Fragen zu beantworten, im Laufe seines Lebens angeeignet. Einem Computer muss dieses Wissen explizit mitgeteilt werden. Tim vor der Brück beschreibt einen Ansatz, wie ein Computer dieses Wissen ähnlich wie ein Mensch durch die Lektüre von Texten erwerben kann. Dabei kommen Methoden der Logik und des maschinellen Lernens zum Einsatz.
@Book{vor:der:Brueck:2012:a, Author = {vor der Brück, Tim}, Title = {Wissensakquisition mithilfe maschineller Lernverfahren auf tiefen semantischen Repr{\"a}sentationen}, Publisher = {Springer}, Address = {Heidelberg, Germany}, abstract = {Eine gro{\ss}e Wissensbasis ist eine Voraussetzung für eine Vielzahl von Anwendungen im Bereich der automatischen Sprachverarbeitung, wie Frage-Antwort- oder Information-Retrieval-Systeme. Ein Mensch hat sich das erforderliche Wissen, um Informationen zu suchen oder Fragen zu beantworten, im Laufe seines Lebens angeeignet. Einem Computer muss dieses Wissen explizit mitgeteilt werden. Tim vor der Brück beschreibt einen Ansatz, wie ein Computer dieses Wissen {\"a}hnlich wie ein Mensch durch die Lektüre von Texten erwerben kann. Dabei kommen Methoden der Logik und des maschinellen Lernens zum Einsatz.}, school = {FernUniversit{\"a}t in Hagen}, year = 2012 }
-
T. vor der Brück and Y. Wang, “Synonymy Extraction from Semantic Networks Using String and Graph Kernel Methods,” in Proceedings of the 20th European Conference on Artificial Intelligence (ECAI), Montpellier, France, 2012, pp. 822-827.
[Abstract] [BibTeX]Synonyms are a highly relevant information source for natural language processing. Automatic synonym extraction methods have in common that they are either applied on the surface representation of the text or on a syntactical structure derived from it. In this paper, however, we present a semantic synonym extraction approach that operates directly on semantic networks (SNs), which were derived from text by a deep syntactico-semantic analysis. Synonymy hypotheses are extracted from the SNs by graph matching. These hypotheses are then validated by a support vector machine (SVM) employing a combined graph and string kernel. Our method was compared to several other approaches and the evaluation has shown that our results are considerably superior
@InProceedings{vor:der:Brueck:Wang:2012, Author = {vor der Brück, Tim and Wang, Yu-Fang}, Title = {Synonymy Extraction from Semantic Networks Using String and Graph Kernel Methods}, BookTitle = {Proceedings of the 20th European Conference on Artificial Intelligence (ECAI)}, Pages = {822--827}, Address = {Montpellier, France}, abstract = {Synonyms are a highly relevant information source for natural language processing. Automatic synonym extraction methods have in common that they are either applied on the surface representation of the text or on a syntactical structure derived from it. In this paper, however, we present a semantic synonym extraction approach that operates directly on semantic networks (SNs), which were derived from text by a deep syntactico-semantic analysis. Synonymy hypotheses are extracted from the SNs by graph matching. These hypotheses are then validated by a support vector machine (SVM) employing a combined graph and string kernel. Our method was compared to several other approaches and the evaluation has shown that our results are considerably superior}, pdf = {http://www.vdb1.de/papers/ECAI_535.pdf}, website = {http://ebooks.iospress.nl/publication/7076}, year = 2012 }
-
T. vor der Brück, “Hyponym Extraction Employing a Weighted Graph Kernel,” in Statistical and Machine Learning Approaches for Network Analysis, M. Dehmer and S. C. Basak, Eds., Hoboken, New Jersey: Wiley, 2012.
[BibTeX]@InCollection{vor:der:Brueck:2012:b, Author = {vor der Brück, Tim}, Title = {Hyponym Extraction Employing a Weighted Graph Kernel}, BookTitle = {Statistical and Machine Learning Approaches for Network Analysis}, Publisher = {Wiley}, Editor = {Matthias Dehmer and Subhash C. Basak}, Address = {Hoboken, New Jersey}, year = 2012 }
-
M. Z. Islam, A. Mehler, and R. Rahman, “Text Readability Classification of Textbooks of a Low-Resource Language,” in Accepted in the 26th Pacific Asia Conference on Language, Information, and Computation (PACLIC 26), 2012.
[Abstract] [BibTeX]There are many languages considered to be low-density languages, either because the population speaking the language is not very large, or because insufficient digitized text material is available in the language even though millions of people speak the language. Bangla is one of the latter ones. Readability classification is an important Natural Language Processing (NLP) application that can be used to judge the quality of documents and assist writers to locate possible problems. This paper presents a readability classifier of Bangla textbook documents based on information-theoretic and lexical features. The features proposed in this paper result in an F-score that is 50% higher than that for traditional readability formulas.
@InProceedings{Islam:Mehler:Rahman:2012, Author = {Islam, Md. Zahurul and Mehler, Alexander and Rahman, Rashedur}, Title = {Text Readability Classification of Textbooks of a Low-Resource Language}, BookTitle = {Accepted in the 26th Pacific Asia Conference on Language, Information, and Computation (PACLIC 26)}, abstract = {There are many languages considered to be low-density languages, either because the population speaking the language is not very large, or because insufficient digitized text material is available in the language even though millions of people speak the language. Bangla is one of the latter ones. Readability classification is an important Natural Language Processing (NLP) application that can be used to judge the quality of documents and assist writers to locate possible problems. This paper presents a readability classifier of Bangla textbook documents based on information-theoretic and lexical features. The features proposed in this paper result in an F-score that is 50% higher than that for traditional readability formulas.}, owner = {zahurul}, pdf = {http://www.aclweb.org/anthology/Y12-1059}, timestamp = {2012.08.14}, website = {http://www.researchgate.net/publication/256648250_Text_Readability_Classification_of_Textbooks_of_a_Low-Resource_Language}, year = 2012 }
-
A. Mehler, L. Romary, and D. Gibbon, “Introduction: Framing Technical Communication,” in Handbook of Technical Communication, A. Mehler, L. Romary, and D. Gibbon, Eds., Berlin and Boston: De Gruyter Mouton, 2012, vol. 8, pp. 1-26.
[BibTeX]@InCollection{Mehler:Romary:Gibbon:2012, Author = {Mehler, Alexander and Romary, Laurent and Gibbon, Dafydd}, Title = {Introduction: Framing Technical Communication}, BookTitle = {Handbook of Technical Communication}, Publisher = {De Gruyter Mouton}, Editor = {Alexander Mehler and Laurent Romary and Dafydd Gibbon}, Volume = {8}, Series = {Handbooks of Applied Linguistics}, Pages = {1-26}, Address = {Berlin and Boston}, year = 2012 }
-
A. Mehler and A. Lücking, “Pathways of Alignment between Gesture and Speech: Assessing Information Transmission in Multimodal Ensembles,” in Proceedings of the International Workshop on Formal and Computational Approaches to Multimodal Communication under the auspices of ESSLLI 2012, Opole, Poland, 6-10 August, 2012.
[Abstract] [BibTeX]We present an empirical account of multimodal ensembles based on Hjelmslev’s notion of selection. This is done to get measurable evidence for the existence of speech-and-gesture ensembles. Utilizing information theory, we show that there is an information transmission that makes a gestures’ representation technique predictable when merely knowing its lexical affiliate – in line with the notion of the primacy of language. Thus, there is evidence for a one-way coupling – going from words to gestures – that leads to speech-and-gesture alignment and underlies the constitution of multimodal ensembles.
@InProceedings{Mehler:Luecking:2012:d, Author = {Mehler, Alexander and Lücking, Andy}, Title = {Pathways of Alignment between Gesture and Speech: Assessing Information Transmission in Multimodal Ensembles}, BookTitle = {Proceedings of the International Workshop on Formal and Computational Approaches to Multimodal Communication under the auspices of ESSLLI 2012, Opole, Poland, 6-10 August}, Editor = {Gianluca Giorgolo and Katya Alahverdzhieva}, abstract = {We present an empirical account of multimodal ensembles based on Hjelmslev’s notion of selection. This is done to get measurable evidence for the existence of speech-and-gesture ensembles. Utilizing information theory, we show that there is an information transmission that makes a gestures’ representation technique predictable when merely knowing its lexical affiliate – in line with the notion of the primacy of language. Thus, there is evidence for a one-way coupling – going from words to gestures – that leads to speech-and-gesture alignment and underlies the constitution of multimodal ensembles.}, keywords = {wikinect}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2016/06/Mehler_Luecking_FoCoMC2012-2.pdf}, website = {http://www.researchgate.net/publication/268368670_Pathways_of_Alignment_between_Gesture_and_Speech_Assessing_Information_Transmission_in_Multimodal_Ensembles}, year = 2012 }
-
A. Lücking, “Towards a Conceptual, Unification-based Speech-Gesture Interface,” in Proceedings of the International Workshop on Formal and Computational Approaches to Multimodal Communication under the auspices of ESSLLI 2012, Opole, Poland, 6-10 August, 2012.
[Abstract] [BibTeX]A framework for grounding the semantics of co-verbal iconic gestures is presented. A resemblance account to iconicity is discarded in favor of an exemplification approach. It is sketched how exemplification can be captured within a unification-based grammar that provides a conceptual interface. Gestures modeled as vector sequences are the exemplificational base. Some hypotheses that follow from the general account are pointed at and remaining challenges are discussed.
@InProceedings{Luecking:2012, Author = {Lücking, Andy}, Title = {Towards a Conceptual, Unification-based Speech-Gesture Interface}, BookTitle = {Proceedings of the International Workshop on Formal and Computational Approaches to Multimodal Communication under the auspices of ESSLLI 2012, Opole, Poland, 6-10 August}, Editor = {Gianluca Giorgolo and Katya Alahverdzhieva}, abstract = {A framework for grounding the semantics of co-verbal iconic gestures is presented. A resemblance account to iconicity is discarded in favor of an exemplification approach. It is sketched how exemplification can be captured within a unification-based grammar that provides a conceptual interface. Gestures modeled as vector sequences are the exemplificational base. Some hypotheses that follow from the general account are pointed at and remaining challenges are discussed.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/FoCoMoC2012-1.pdf}, year = 2012 }
-
A. Mehler and A. Lücking, “WikiNect: Towards a Gestural Writing System for Kinetic Museum Wikis,” in Proceedings of the International Workshop On User Experience in e-Learning and Augmented Technologies in Education (UXeLATE 2012) in Conjunction with ACM Multimedia 2012, 29 October- 2 November, Nara, Japan, 2012, pp. 7-12.
[Abstract] [BibTeX]We introduce WikiNect as a kinetic museum information system that allows museum visitors to give on-site feedback about exhibitions. To this end, WikiNect integrates three approaches to Human-Computer Interaction (HCI): games with a purpose, wiki-based collaborative writing and kinetic text-technologies. Our aim is to develop kinetic technologies as a new paradigm of HCI. They dispense with classical interfaces (e.g., keyboards) in that they build on non-contact modes of communication like gestures or facial expressions as input displays. In this paper, we introduce the notion of gestural writing as a kinetic text-technology that underlies WikiNect to enable museum visitors to communicate their feedback. The basic idea is to explore sequences of gestures that share the semantic expressivity of verbally manifested speech acts. Our task is to identify such gestures that are learnable on-site in the usage scenario of WikiNect. This is done by referring to so-called transient gestures as part of multimodal ensembles, which are candidate gestures of the desired functionality.
@InProceedings{Mehler:Luecking:2012:c, Author = {Mehler, Alexander and Lücking, Andy}, Title = {WikiNect: Towards a Gestural Writing System for Kinetic Museum Wikis}, BookTitle = {Proceedings of the International Workshop On User Experience in e-Learning and Augmented Technologies in Education (UXeLATE 2012) in Conjunction with ACM Multimedia 2012, 29 October- 2 November, Nara, Japan}, Pages = {7-12}, abstract = {We introduce WikiNect as a kinetic museum information system that allows museum visitors to give on-site feedback about exhibitions. To this end, WikiNect integrates three approaches to Human-Computer Interaction (HCI): games with a purpose, wiki-based collaborative writing and kinetic text-technologies. Our aim is to develop kinetic technologies as a new paradigm of HCI. They dispense with classical interfaces (e.g., keyboards) in that they build on non-contact modes of communication like gestures or facial expressions as input displays. In this paper, we introduce the notion of gestural writing as a kinetic text-technology that underlies WikiNect to enable museum visitors to communicate their feedback. The basic idea is to explore sequences of gestures that share the semantic expressivity of verbally manifested speech acts. Our task is to identify such gestures that are learnable on-site in the usage scenario of WikiNect. This is done by referring to so-called transient gestures as part of multimodal ensembles, which are candidate gestures of the desired functionality. }, keywords = {wikinect}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/UXeLATE2012-copyright.pdf}, website = {http://www.researchgate.net/publication/262319200_WikiNect_towards_a_gestural_writing_system_for_kinetic_museum_wikis}, year = 2012 }
-
R. Gleim, A. Mehler, and A. Ernst, “SOA implementation of the eHumanities Desktop,” in Proceedings of the Workshop on Service-oriented Architectures (SOAs) for the Humanities: Solutions and Impacts, Digital Humanities 2012, Hamburg, Germany, 2012.
[Abstract] [BibTeX]The eHumanities Desktop is a system which allows users to upload, organize and share resources using a web interface. Furthermore resources can be processed, annotated and analyzed in various ways. Registered users can organize themselves in groups and collaboratively work on their data. The eHumanities Desktop is platform independent and runs in a web browser. This paper presents the system focusing on its service orientation and process management.
@InProceedings{Gleim:Mehler:Ernst:2012, Author = {Gleim, Rüdiger and Mehler, Alexander and Ernst, Alexandra}, Title = {SOA implementation of the eHumanities Desktop}, BookTitle = {Proceedings of the Workshop on Service-oriented Architectures (SOAs) for the Humanities: Solutions and Impacts, Digital Humanities 2012, Hamburg, Germany}, abstract = {The eHumanities Desktop is a system which allows users to upload, organize and share resources using a web interface. Furthermore resources can be processed, annotated and analyzed in various ways. Registered users can organize themselves in groups and collaboratively work on their data. The eHumanities Desktop is platform independent and runs in a web browser. This paper presents the system focusing on its service orientation and process management.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/dhc2012.pdf}, year = 2012 }
-
A. Mehler and C. Stegbauer, “On the Self-similarity of Intertextual Structures in Wikipedia,” in Proceedings of the HotSocial ’12: The First ACM International Workshop on Hot Topics on Interdisciplinary Social Networks Research, Beijing, China, 2012, pp. 65-68.
[BibTeX]@InProceedings{Mehler:Stegbauer:2012, Author = {Mehler, Alexander and Stegbauer, Christian}, Title = {On the Self-similarity of Intertextual Structures in Wikipedia}, BookTitle = {Proceedings of the HotSocial '12: The First ACM International Workshop on Hot Topics on Interdisciplinary Social Networks Research}, Editor = {Xiaoming Fu and Peter Gloor and Jie Tang}, Pages = {65-68}, Address = {Beijing, China}, pdf = {http://wan.poly.edu/KDD2012/forms/workshop/HotSocial12/doc/p64_mehler.pdf}, website = {http://dl.acm.org/citation.cfm?id=2392633&bnc=1}, year = 2012 }
-
A. Mehler, S. Schwandt, R. Gleim, and A. Ernst, “Inducing Linguistic Networks from Historical Corpora: Towards a New Method in Historical Semantics,” in Proceedings of the Conference on New Methods in Historical Corpora, P. Bennett, M. Durrell, S. Scheible, and R. J. Whitt, Eds., Tübingen: Narr, 2012, vol. 3, pp. 257-274.
[BibTeX]@InCollection{Mehler:Schwandt:Gleim:Ernst:2012, Author = {Mehler, Alexander and Schwandt, Silke and Gleim, Rüdiger and Ernst, Alexandra}, Title = {Inducing Linguistic Networks from Historical Corpora: Towards a New Method in Historical Semantics}, BookTitle = {Proceedings of the Conference on New Methods in Historical Corpora}, Publisher = {Narr}, Editor = {Paul Bennett and Martin Durrell and Silke Scheible and Richard J. Whitt}, Volume = {3}, Series = {Corpus linguistics and Interdisciplinary perspectives on language (CLIP)}, Pages = {257--274}, Address = {Tübingen}, year = 2012 }
-
A. Lücking, S. Ptock, and K. Bergmann, “Assessing Agreement on Segmentations by Means of Staccato, the Segmentation Agreement Calculator according to Thomann,” in Gesture and Sign Language in Human-Computer Interaction and Embodied Communication, E. Efthimiou, G. Kouroupetroglou, and S. Fotina, Eds., Berlin and Heidelberg: Springer, 2012, vol. 7206, pp. 129-138.
[Abstract] [BibTeX]Staccato, the Segmentation Agreement Calculator According to Thomann , is a software tool for assessing the degree of agreement of multiple segmentations of some time-related data (e.g., gesture phases or sign language constituents). The software implements an assessment procedure developed by Bruno Thomann and will be made publicly available. The article discusses the rationale of the agreement assessment procedure and points at future extensions of Staccato.
@InCollection{Luecking:Ptock:Bergmann:2012, Author = {Lücking, Andy and Ptock, Sebastian and Bergmann, Kirsten}, Title = {Assessing Agreement on Segmentations by Means of Staccato, the Segmentation Agreement Calculator according to Thomann}, BookTitle = {Gesture and Sign Language in Human-Computer Interaction and Embodied Communication}, Publisher = {Springer}, Editor = {Eleni Efthimiou and Georgios Kouroupetroglou and Stavroula-Evita Fotina}, Volume = {7206}, Series = {Lecture Notes in Artificial Intelligence}, Pages = {129-138}, Address = {Berlin and Heidelberg}, abstract = {Staccato, the Segmentation Agreement Calculator According to Thomann , is a software tool for assessing the degree of agreement of multiple segmentations of some time-related data (e.g., gesture phases or sign language constituents). The software implements an assessment procedure developed by Bruno Thomann and will be made publicly available. The article discusses the rationale of the agreement assessment procedure and points at future extensions of Staccato.}, booksubtitle = {9th International Gesture Workshop, GW 2011, Athens, Greece, May 2011, Revised Selected Papers}, website = {http://link.springer.com/chapter/10.1007/978-3-642-34182-3_12}, year = 2012 }
-
A. Mehler, A. Lücking, and P. Menke, “Assessing Cognitive Alignment in Different Types of Dialog by means of a Network Model,” Neural Networks, vol. 32, pp. 159-164, 2012.
[Abstract] [BibTeX]We present a network model of dialog lexica, called TiTAN (Two-layer Time-Aligned Network) series. TiTAN series capture the formation and structure of dialog lexica in terms of serialized graph representations. The dynamic update of TiTAN series is driven by the dialog-inherent timing of turn-taking. The model provides a link between neural, connectionist underpinnings of dialog lexica on the one hand and observable symbolic behavior on the other. On the neural side, priming and spreading activation are modeled in terms of TiTAN networking. On the symbolic side, TiTAN series account for cognitive alignment in terms of the structural coupling of the linguistic representations of dialog partners. This structural stance allows us to apply TiTAN in machine learning of data of dialogical alignment. In previous studies, it has been shown that aligned dialogs can be distinguished from non-aligned ones by means of TiTAN -based modeling. Now, we simultaneously apply this model to two types of dialog: task-oriented, experimentally controlled dialogs on the one hand and more spontaneous, direction giving dialogs on the other. We ask whether it is possible to separate aligned dialogs from non-aligned ones in a type-crossing way. Starting from a recent experiment (Mehler, Lücking, & Menke, 2011a), we show that such a type-crossing classification is indeed possible. This hints at a structural fingerprint left by alignment in networks of linguistic items that are routinely co-activated during conversation.
@Article{Mehler:Luecking:Menke:2012, Author = {Mehler, Alexander and Lücking, Andy and Menke, Peter}, Title = {Assessing Cognitive Alignment in Different Types of Dialog by means of a Network Model}, Journal = {Neural Networks}, Volume = {32}, Pages = {159-164}, abstract = {We present a network model of dialog lexica, called TiTAN (Two-layer Time-Aligned Network) series. TiTAN series capture the formation and structure of dialog lexica in terms of serialized graph representations. The dynamic update of TiTAN series is driven by the dialog-inherent timing of turn-taking. The model provides a link between neural, connectionist underpinnings of dialog lexica on the one hand and observable symbolic behavior on the other. On the neural side, priming and spreading activation are modeled in terms of TiTAN networking. On the symbolic side, TiTAN series account for cognitive alignment in terms of the structural coupling of the linguistic representations of dialog partners. This structural stance allows us to apply TiTAN in machine learning of data of dialogical alignment. In previous studies, it has been shown that aligned dialogs can be distinguished from non-aligned ones by means of TiTAN -based modeling. Now, we simultaneously apply this model to two types of dialog: task-oriented, experimentally controlled dialogs on the one hand and more spontaneous, direction giving dialogs on the other. We ask whether it is possible to separate aligned dialogs from non-aligned ones in a type-crossing way. Starting from a recent experiment (Mehler, Lücking, \& Menke, 2011a), we show that such a type-crossing classification is indeed possible. This hints at a structural fingerprint left by alignment in networks of linguistic items that are routinely co-activated during conversation.}, doi = {10.1016/j.neunet.2012.02.013}, website = {http://www.sciencedirect.com/science/article/pii/S0893608012000421}, year = 2012 }
-
M. Z. Islam and A. Mehler, “Customization of the Europarl Corpus for Translation Studies,” in Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC), 2012.
[Abstract] [BibTeX]Currently, the area of translation studies lacks corpora by which translation scholars can validate their theoretical claims, for example, regarding the scope of the characteristics of the translation relation. In this paper, we describe a customized resource in the area of translation studies that mainly addresses research on the properties of the translation relation. Our experimental results show that the Type-Token-Ratio (TTR) is not a universally valid indicator of the simplification of translation.
@InProceedings{Islam:Mehler:2012:a, Author = {Islam, Md. Zahurul and Mehler, Alexander}, Title = {Customization of the Europarl Corpus for Translation Studies}, BookTitle = {Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC)}, abstract = {Currently, the area of translation studies lacks corpora by which translation scholars can validate their theoretical claims, for example, regarding the scope of the characteristics of the translation relation. In this paper, we describe a customized resource in the area of translation studies that mainly addresses research on the properties of the translation relation. Our experimental results show that the Type-Token-Ratio (TTR) is not a universally valid indicator of the simplification of translation.}, owner = {zahurul}, pdf = {http://www.lrec-conf.org/proceedings/lrec2012/pdf/729_Paper.pdf}, timestamp = {2012.02.02}, year = 2012 }
-
A. Lücking and T. Pfeiffer, “Framing Multimodal Technical Communication. With Focal Points in Speech-Gesture-Integration and Gaze Recognition,” in Handbook of Technical Communication, A. Mehler, L. Romary, and D. Gibbon, Eds., De Gruyter Mouton, 2012, vol. 8, pp. 591-644.
[BibTeX]@InCollection{Luecking:Pfeiffer:2012, Author = {Lücking, Andy and Pfeiffer, Thies}, Title = {Framing Multimodal Technical Communication. With Focal Points in Speech-Gesture-Integration and Gaze Recognition}, BookTitle = {Handbook of Technical Communication}, Publisher = {De Gruyter Mouton}, Editor = {Alexander Mehler and Laurent Romary and Dafydd Gibbon}, Volume = {8}, Series = {Handbooks of Applied Linguistics}, Chapter = {18}, Pages = {591-644}, website = {http://www.degruyter.com/view/books/9783110224948/9783110224948.591/9783110224948.591.xml}, year = 2012 }
-
P. Kubina, O. Abramov, and A. Lücking, “Barrier-free Communication,” in Handbook of Technical Communication, A. Mehler and L. Romary, Eds., Berlin and Boston: De Gruyter Mouton, 2012, vol. 8, pp. 645-706.
[BibTeX]@InCollection{Kubina:Abramov:Luecking:2012, Author = {Kubina, Petra and Abramov, Olga and Lücking, Andy}, Title = {Barrier-free Communication}, BookTitle = {Handbook of Technical Communication}, Publisher = {De Gruyter Mouton}, Editor = {Alexander Mehler and Laurent Romary}, Volume = {8}, Series = {Handbooks of Applied Linguistics}, Chapter = {19}, Pages = {645-706}, Address = {Berlin and Boston}, editora = {Dafydd Gibbon}, editoratype = {collaborator}, website = {http://www.degruyter.com/view/books/9783110224948/9783110224948.645/9783110224948.645.xml}, year = 2012 }
-
A. Lücking and A. Mehler, “What’s the Scope of the Naming Game? Constraints on Semantic Categorization,” in Proceedings of the 9th International Conference on the Evolution of Language, Kyoto, Japan, 2012, pp. 196-203.
[Abstract] [BibTeX]The Naming Game (NG) has become a vivid research paradigm for simulation studies on language evolution and the establishment of naming conventions. Recently, NGs were used for reconstructing the creation of linguistic categories, most notably for color terms. We recap the functional principle of NGs and the latter Categorization Games (CGs) and evaluate them in the light of semantic data of linguistic categorization outside the domain of colors. This comparison reveals two specifics of the CG paradigm: Firstly, the emerging categories draw basically on the predefined topology of the learning domain. Secondly, the kind of categories that can be learnt in CGs is bound to context-independent intersective categories. This suggests that the NG and the CG focus on a special aspect of natural language categorization, which disregards context-sensitive categories used in a non-compositional manner.
@InProceedings{Luecking:Mehler:2012, Author = {Lücking, Andy and Mehler, Alexander}, Title = {What's the Scope of the Naming Game? Constraints on Semantic Categorization}, BookTitle = {Proceedings of the 9th International Conference on the Evolution of Language}, Pages = {196-203}, Address = {Kyoto, Japan}, abstract = {The Naming Game (NG) has become a vivid research paradigm for simulation studies on language evolution and the establishment of naming conventions. Recently, NGs were used for reconstructing the creation of linguistic categories, most notably for color terms. We recap the functional principle of NGs and the latter Categorization Games (CGs) and evaluate them in the light of semantic data of linguistic categorization outside the domain of colors. This comparison reveals two specifics of the CG paradigm: Firstly, the emerging categories draw basically on the predefined topology of the learning domain. Secondly, the kind of categories that can be learnt in CGs is bound to context-independent intersective categories. This suggests that the NG and the CG focus on a special aspect of natural language categorization, which disregards context-sensitive categories used in a non-compositional manner.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Evolang2012-AL_AM.pdf}, url = {http://kyoto.evolang.org/}, website = {https://www.researchgate.net/publication/267858061_WHAT'S_THE_SCOPE_OF_THE_NAMING_GAME_CONSTRAINTS_ON_SEMANTIC_CATEGORIZATION}, year = 2012 }
-
M. Sukhareva, M. Z. Islam, A. Hoenen, and A. Mehler, “A Three-step Model of Language Detection in Multilingual Ancient Texts,” in Proceedings of Workshop on Annotation of Corpora for Research in the Humanities, Heidelberg, Germany, 2012.
[Abstract] [BibTeX]Ancient corpora contain various multilingual patterns. This imposes numerous problems on their manual annotation and automatic processing. We introduce a lexicon building system, called Lexicon Expander, that has an integrated language detection module, Language Detection (LD) Toolkit. The Lexicon Expander post-processes the output of the LD Toolkit which leads to the improvement of f-score and accuracy values. Furthermore, the functionality of the Lexicon Expander also includes manual editing of lexical entries and automatic morphological expansion by means of a morphological grammar.
@InProceedings{Sukhareva:Islam:Hoenen:Mehler:2012, Author = {Sukhareva, Maria and Islam, Md. Zahurul and Hoenen, Armin and Mehler, Alexander}, Title = {A Three-step Model of Language Detection in Multilingual Ancient Texts}, BookTitle = {Proceedings of Workshop on Annotation of Corpora for Research in the Humanities}, Address = {Heidelberg, Germany}, abstract = {Ancient corpora contain various multilingual patterns. This imposes numerous problems on their manual annotation and automatic processing. We introduce a lexicon building system, called Lexicon Expander, that has an integrated language detection module, Language Detection (LD) Toolkit. The Lexicon Expander post-processes the output of the LD Toolkit which leads to the improvement of f-score and accuracy values. Furthermore, the functionality of the Lexicon Expander also includes manual editing of lexical entries and automatic morphological expansion by means of a morphological grammar.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/sukhareva_islam_hoenen_mehler_2011.pdf}, website = {https://www.academia.edu/2236625/A_Three-step_Model_of_Language_Detection_in_Multilingual_Ancient_Texts}, year = 2012 }
2011 (25)
-
A. Lücking and A. Mehler, “A Model of Complexity Levels of Meaning Constitution in Simulation Models of Language Evolution,” International Journal of Signs and Semiotic Systems, vol. 1, iss. 1, pp. 18-38, 2011.
[Abstract] [BibTeX]Currently, some simulative accounts exist within dynamic or evolutionary frameworks that are concerned with the development of linguistic categories within a population of language users. Although these studies mostly emphasize that their models are abstract, the paradigm categorization domain is preferably that of colors. In this paper, the authors argue that color adjectives are special predicates in both linguistic and metaphysical terms: semantically, they are intersective predicates, metaphysically, color properties can be empirically reduced onto purely physical properties. The restriction of categorization simulations to the color paradigm systematically leads to ignoring two ubiquitous features of natural language predicates, namely relativity and context-dependency. Therefore, the models for simulation models of linguistic categories are not able to capture the formation of categories like perspective-dependent predicates ‘left’ and ‘right’, subsective predicates like ‘small’ and ‘big’, or predicates that make reference to abstract objects like ‘I prefer this kind of situation’. The authors develop a three-dimensional grid of ascending complexity that is partitioned according to the semiotic triangle. They also develop a conceptual model in the form of a decision grid by means of which the complexity level of simulation models of linguistic categorization can be assessed in linguistic terms.
@Article{Luecking:Mehler:2011, Author = {Lücking, Andy and Mehler, Alexander}, Title = {A Model of Complexity Levels of Meaning Constitution in Simulation Models of Language Evolution}, Journal = {International Journal of Signs and Semiotic Systems}, Volume = {1}, Number = {1}, Pages = {18-38}, abstract = {Currently, some simulative accounts exist within dynamic or evolutionary frameworks that are concerned with the development of linguistic categories within a population of language users. Although these studies mostly emphasize that their models are abstract, the paradigm categorization domain is preferably that of colors. In this paper, the authors argue that color adjectives are special predicates in both linguistic and metaphysical terms: semantically, they are intersective predicates, metaphysically, color properties can be empirically reduced onto purely physical properties. The restriction of categorization simulations to the color paradigm systematically leads to ignoring two ubiquitous features of natural language predicates, namely relativity and context-dependency. Therefore, the models for simulation models of linguistic categories are not able to capture the formation of categories like perspective-dependent predicates ‘left’ and ‘right’, subsective predicates like ‘small’ and ‘big’, or predicates that make reference to abstract objects like ‘I prefer this kind of situation’. The authors develop a three-dimensional grid of ascending complexity that is partitioned according to the semiotic triangle. They also develop a conceptual model in the form of a decision grid by means of which the complexity level of simulation models of linguistic categorization can be assessed in linguistic terms.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/luecking_mehler_article_IJSSS.pdf}, year = 2011 }
-
A. Mehler, O. Abramov, and N. Diewald, “Geography of Social Ontologies: Testing a Variant of the Sapir-Whorf Hypothesis in the Context of Wikipedia,” Computer Speech and Language, vol. 25, iss. 3, pp. 716-740, 2011.
[Abstract] [BibTeX]In this article, we test a variant of the Sapir-Whorf Hypothesis in the area of complex network theory. This is done by analyzing social ontologies as a new resource for automatic language classification. Our method is to solely explore structural features of social ontologies in order to predict family resemblances of languages used by the corresponding communities to build these ontologies. This approach is based on a reformulation of the Sapir-Whorf Hypothesis in terms of distributed cognition. Starting from a corpus of 160 Wikipedia-based social ontologies, we test our variant of the Sapir-Whorf Hypothesis by several experiments, and find out that we outperform the corresponding baselines. All in all, the article develops an approach to classify linguistic networks of tens of thousands of vertices by exploring a small range of mathematically well-established topological indices.
@Article{Mehler:Abramov:Diewald:2011:a, Author = {Mehler, Alexander and Abramov, Olga and Diewald, Nils}, Title = {Geography of Social Ontologies: Testing a Variant of the Sapir-Whorf Hypothesis in the Context of Wikipedia}, Journal = {Computer Speech and Language}, Volume = {25}, Number = {3}, Pages = {716-740}, abstract = {In this article, we test a variant of the Sapir-Whorf Hypothesis in the area of complex network theory. This is done by analyzing social ontologies as a new resource for automatic language classification. Our method is to solely explore structural features of social ontologies in order to predict family resemblances of languages used by the corresponding communities to build these ontologies. This approach is based on a reformulation of the Sapir-Whorf Hypothesis in terms of distributed cognition. Starting from a corpus of 160 Wikipedia-based social ontologies, we test our variant of the Sapir-Whorf Hypothesis by several experiments, and find out that we outperform the corresponding baselines. All in all, the article develops an approach to classify linguistic networks of tens of thousands of vertices by exploring a small range of mathematically well-established topological indices.}, doi = {10.1016/j.csl.2010.05.006}, website = {http://www.sciencedirect.com/science/article/pii/S0885230810000434}, year = 2011 }
-
A. Mehler, “Social Ontologies as Generalized Nearly Acyclic Directed Graphs: A Quantitative Graph Model of Social Ontologies by Example of Wikipedia,” in Towards an Information Theory of Complex Networks: Statistical Methods and Applications, M. Dehmer, F. Emmert-Streib, and A. Mehler, Eds., Boston/Basel: Birkhäuser, 2011, pp. 259-319.
[BibTeX]@InCollection{Mehler:2011:c, Author = {Mehler, Alexander}, Title = {Social Ontologies as Generalized Nearly Acyclic Directed Graphs: A Quantitative Graph Model of Social Ontologies by Example of Wikipedia}, BookTitle = {Towards an Information Theory of Complex Networks: Statistical Methods and Applications}, Publisher = {Birkh{\"a}user}, Editor = {Dehmer, Matthias and Emmert-Streib, Frank and Mehler, Alexander}, Pages = {259-319}, Address = {Boston/Basel}, year = 2011 }
-
A. Lücking, S. Ptock, and K. Bergmann, “Staccato: Segmentation Agreement Calculator,” in Gesture in Embodied Communication and Human-Computer Interaction. Proceedings of the 9th International Gesture Workshop, Athens, Greece, 2011, pp. 50-53.
[BibTeX]@InProceedings{Luecking:Ptock:Bergmann:2011, Author = {Lücking, Andy and Ptock, Sebastian and Bergmann, Kirsten}, Title = {Staccato: Segmentation Agreement Calculator}, BookTitle = {Gesture in Embodied Communication and Human-Computer Interaction. Proceedings of the 9th International Gesture Workshop}, Editor = {Eleni Efthimiou and Georgios Kouroupetroglou}, Series = {GW 2011}, Pages = {50--53}, Address = {Athens, Greece}, Publisher = {National and Kapodistrian University of Athens}, month = {5}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/LueckingEA_final.pdf}, year = 2011 }
-
A. Mehler and A. Lücking, “A Graph Model of Alignment in Multilog,” in Proceedings of IEEE Africon 2011, Zambia, 2011.
[BibTeX]@InProceedings{Mehler:Luecking:2011, Author = {Mehler, Alexander and Lücking, Andy}, Title = {A Graph Model of Alignment in Multilog}, BookTitle = {Proceedings of IEEE Africon 2011}, Series = {IEEE Africon}, Address = {Zambia}, Organization = {IEEE}, month = {9}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/africon2011-paper-Alexander_Mehler_Andy_Luecking.pdf}, website = {https://www.researchgate.net/publication/267941012_A_Graph_Model_of_Alignment_in_Multilog}, year = 2011 }
-
C. Stegbauer and A. Mehler, “Positionssensitive Dekomposition von Potenzgesetzen am Beispiel von Wikipedia-basierten Kollaborationsnetzwerken,” in Proceedings of the 4th Workshop Digital Social Networks at INFORMATIK 2011: Informatik schafft Communities, Oct 4-7, 2011, Berlin, 2011.
[BibTeX]@InProceedings{Stegbauer:Mehler:2011, Author = {Stegbauer, Christian and Mehler, Alexander}, Title = {Positionssensitive Dekomposition von Potenzgesetzen am Beispiel von Wikipedia-basierten Kollaborationsnetzwerken}, BookTitle = {Proceedings of the 4th Workshop Digital Social Networks at INFORMATIK 2011: Informatik schafft Communities, Oct 4-7, 2011, Berlin}, pdf = {http://www.user.tu-berlin.de/komm/CD/paper/090423.pdf}, specialnote = {Best Paper Award}, specialnotewebsite = {http://www.digitale-soziale-netze.de/gi-workshop/index.php?site=review2011}, year = 2011 }
-
M. Lösch, U. Waltinger, W. Horstmann, and A. Mehler, “Building a DDC-annotated Corpus from OAI Metadata,” Journal of Digital Information, vol. 12, iss. 2, 2011.
[Abstract] [BibTeX]Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surface-oriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score.
@Article{Loesch:Waltinger:Horstmann:Mehler:2011, Author = {Lösch, Mathias and Waltinger, Ulli and Horstmann, Wolfram and Mehler, Alexander}, Title = {Building a DDC-annotated Corpus from OAI Metadata}, Journal = {Journal of Digital Information}, Volume = {12}, Number = {2}, abstract = {Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surface-oriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score.}, bibsource = {DBLP, http://dblp.uni-trier.de}, pdf = {https://journals.tdl.org/jodi/index.php/jodi/article/download/1765/1767}, website = {http://journals.tdl.org/jodi/article/view/1765}, year = 2011 }
-
M. Lux, J. Laußmann, A. Mehler, and C. Menßen, “An Online Platform for Visualizing Time Series in Linguistic Networks,” in Proceedings of the Demonstrations Session of the 2011 IEEE / WIC / ACM International Conferences on Web Intelligence and Intelligent Agent Technology, 22 – 27 August 2011, Lyon, France, 2011.
[Poster][BibTeX]@InProceedings{Lux:Laussmann:Mehler:Menssen:2011, Author = {Lux, Markus and Lau{\ss}mann, Jan and Mehler, Alexander and Men{\ss}en, Christian}, Title = {An Online Platform for Visualizing Time Series in Linguistic Networks}, BookTitle = {Proceedings of the Demonstrations Session of the 2011 IEEE / WIC / ACM International Conferences on Web Intelligence and Intelligent Agent Technology, 22 - 27 August 2011, Lyon, France}, poster = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/wi-iat-poster-2011.pdf}, website = {http://dl.acm.org/citation.cfm?id=2052396}, year = 2011 }
-
A. Mehler, N. Diewald, U. Waltinger, R. Gleim, D. Esch, B. Job, T. Küchelmann, O. Abramov, and P. Blanchard, “Evolution of Romance Language in Written Communication: Network Analysis of Late Latin and Early Romance Corpora,” Leonardo, vol. 44, iss. 3, 2011.
[BibTeX]@Article{Mehler:Diewald:Waltinger:et:al:2010, Author = {Mehler, Alexander and Diewald, Nils and Waltinger, Ulli and Gleim, Rüdiger and Esch, Dietmar and Job, Barbara and Küchelmann, Thomas and Abramov, Olga and Blanchard, Philippe}, Title = {Evolution of Romance Language in Written Communication: Network Analysis of Late Latin and Early Romance Corpora}, Journal = {Leonardo}, Volume = {44}, Number = {3}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_diewald_waltinger_gleim_esch_job_kuechelmann_pustylnikov_blanchard_2010.pdf}, publisher = {MIT Press}, year = 2011 }
-
A. Mehler, A. Lücking, and P. Menke, “From Neural Activation to Symbolic Alignment: A Network-Based Approach to the Formation of Dialogue Lexica,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN 2011), San Jose, California, July 31 — August 5, 2011.
[BibTeX]@InProceedings{Mehler:Luecking:Menke:2011, Author = {Mehler, Alexander and Lücking, Andy and Menke, Peter}, Title = {From Neural Activation to Symbolic Alignment: A Network-Based Approach to the Formation of Dialogue Lexica}, BookTitle = {Proceedings of the International Joint Conference on Neural Networks (IJCNN 2011), San Jose, California, July 31 -- August 5}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/neural-align-final.pdf}, website = {{http://dx.doi.org/10.1109/IJCNN.2011.6033266}}, year = 2011 }
-
A. Lücking, O. Abramov, A. Mehler, and P. Menke, “The Bielefeld Jigsaw Map Game (JMG) Corpus,” in Abstracts of the Corpus Linguistics Conference 2011, Birmingham, 2011.
[BibTeX]@InProceedings{Luecking:Abramov:Mehler:Menke:2011, Author = {Lücking, Andy and Abramov, Olga and Mehler, Alexander and Menke, Peter}, Title = {The Bielefeld Jigsaw Map Game (JMG) Corpus}, BookTitle = {Abstracts of the Corpus Linguistics Conference 2011}, Series = {CL2011}, Address = {Birmingham}, pdf = {http://www.birmingham.ac.uk/documents/college-artslaw/corpus/conference-archives/2011/Paper-137.pdf}, website = {http://www.birmingham.ac.uk/research/activity/corpus/publications/conference-archives/2011-birmingham.aspx}, year = 2011 }
-
R. Gleim, A. Hoenen, N. Diewald, A. Mehler, and A. Ernst, “Modeling, Building and Maintaining Lexica for Corpus Linguistic Studies by Example of Late Latin,” in Corpus Linguistics 2011, 20-22 July, Birmingham, 2011.
[BibTeX]@InProceedings{Gleim:Hoenen:Diewald:Mehler:Ernst:2011, Author = {Gleim, Rüdiger and Hoenen, Armin and Diewald, Nils and Mehler, Alexander and Ernst, Alexandra}, Title = {Modeling, Building and Maintaining Lexica for Corpus Linguistic Studies by Example of Late Latin}, BookTitle = {Corpus Linguistics 2011, 20-22 July, Birmingham}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Paper-48.pdf}, year = 2011 }
-
P. Menke and A. Mehler, “From experiments to corpora: The Ariadne Corpus Management System,” in Corpus Linguistics 2011, 20-22 July, Birmingham, 2011.
[BibTeX]@InProceedings{Menke:Mehler:2011, Author = {Menke, Peter and Mehler, Alexander}, Title = {From experiments to corpora: The Ariadne Corpus Management System}, BookTitle = {Corpus Linguistics 2011, 20-22 July, Birmingham}, website = {https://www.researchgate.net/publication/260186214_From_Experiments_to_Corpora_The_Ariadne_Corpus_Management_System}, year = 2011 }
-
Towards an Information Theory of Complex Networks: Statistical Methods and Applications, M. Dehmer, F. Emmert-Streib, and A. Mehler, Eds., Boston/Basel: Birkhäuser, 2011.
[BibTeX]@Book{Dehmer:EmmertStreib:Mehler:2009:a, Editor = {Dehmer, Matthias and Emmert-Streib, Frank and Mehler, Alexander}, Title = {Towards an Information Theory of Complex Networks: Statistical Methods and Applications}, Publisher = {Birkh{\"a}user}, Address = {Boston/Basel}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/InformationTheoryComplexNetworks.jpg}, pagetotal = {395}, website = {http://link.springer.com/book/10.1007/978-0-8176-4904-3/page/1}, year = 2011 }
-
A. Mehler, A. Lücking, and P. Menke, “Assessing Lexical Alignment in Spontaneous Direction Dialogue Data by Means of a Lexicon Network Model,” in Proceedings of 12th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), February 20–26, Tokyo, Berlin/New York, 2011, pp. 368-379.
[BibTeX]@InProceedings{Mehler:Luecking:Menke:2011:a, Author = {Mehler, Alexander and Lücking, Andy and Menke, Peter}, Title = {Assessing Lexical Alignment in Spontaneous Direction Dialogue Data by Means of a Lexicon Network Model}, BookTitle = {Proceedings of 12th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), February 20--26, Tokyo}, Series = {CICLing'11}, Pages = {368-379}, Address = {Berlin/New York}, Publisher = {Springer}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/titan-cicling-camera-ready.pdf}, website = {http://www.springerlink.com/content/g7p2250025u20010/}, year = 2011 }
-
P. Geibel, A. Mehler, and K. Kühnberger, “Learning Methods for Graph Models of Document Structure,” in Modeling, Learning and Processing of Text Technological Data Structures, A. Mehler, K. Kühnberger, H. Lobin, H. Lüngen, A. Storrer, and A. Witt, Eds., Berlin/New York: Springer, 2011.
[BibTeX]@InCollection{Geibel:Mehler:Kuehnberger:2011:a, Author = {Geibel, Peter and Mehler, Alexander and Kühnberger, Kai-Uwe}, Title = {Learning Methods for Graph Models of Document Structure}, BookTitle = {Modeling, Learning and Processing of Text Technological Data Structures}, Publisher = {Springer}, Editor = {Mehler, Alexander and Kühnberger, Kai-Uwe and Lobin, Henning and Lüngen, Harald and Storrer, Angelika and Witt, Andreas}, Series = {Studies in Computational Intelligence}, Address = {Berlin/New York}, website = {http://www.springerlink.com/content/p095331472h76v56/}, year = 2011 }
-
A. Mehler and U. Waltinger, “Integrating Content and Structure Learning: A Model of Hypertext Zoning and Sounding,” in Modeling, Learning and Processing of Text Technological Data Structures, A. Mehler, K. Kühnberger, H. Lobin, H. Lüngen, A. Storrer, and A. Witt, Eds., Berlin/New York: Springer, 2011.
[BibTeX]@InCollection{Mehler:Waltinger:2011:a, Author = {Mehler, Alexander and Waltinger, Ulli}, Title = {Integrating Content and Structure Learning: A Model of Hypertext Zoning and Sounding}, BookTitle = {Modeling, Learning and Processing of Text Technological Data Structures}, Publisher = {Springer}, Editor = {Mehler, Alexander and Kühnberger, Kai-Uwe and Lobin, Henning and Lüngen, Harald and Storrer, Angelika and Witt, Andreas}, Series = {Studies in Computational Intelligence}, Address = {Berlin/New York}, website = {http://rd.springer.com/chapter/10.1007/978-3-642-22613-7_15}, year = 2011 }
-
O. Abramov and A. Mehler, “Automatic Language Classification by Means of Syntactic Dependency Networks,” Journal of Quantitative Linguistics, vol. 18, iss. 4, pp. 291-336, 2011.
[Abstract] [BibTeX]This article presents an approach to automatic language classification by means of linguistic networks. Networks of 11 languages were constructed from dependency treebanks, and the topology of these networks serves as input to the classification algorithm. The results match the genealogical similarities of these languages. In addition, we test two alternative approaches to automatic language classification – one based on n-grams and the other on quantitative typological indices. All three methods show good results in identifying genealogical groups. Beyond genetic similarities, network features (and feature combinations) offer a new source of typological information about languages. This information can contribute to a better understanding of the interplay of single linguistic phenomena observed in language.
@Article{Abramov:Mehler:2011:a, Author = {Abramov, Olga and Mehler, Alexander}, Title = {Automatic Language Classification by Means of Syntactic Dependency Networks}, Journal = {Journal of Quantitative Linguistics}, Volume = {18}, Number = {4}, Pages = {291-336}, abstract = {This article presents an approach to automatic language classification by means of linguistic networks. Networks of 11 languages were constructed from dependency treebanks, and the topology of these networks serves as input to the classification algorithm. The results match the genealogical similarities of these languages. In addition, we test two alternative approaches to automatic language classification – one based on n-grams and the other on quantitative typological indices. All three methods show good results in identifying genealogical groups. Beyond genetic similarities, network features (and feature combinations) offer a new source of typological information about languages. This information can contribute to a better understanding of the interplay of single linguistic phenomena observed in language.}, website = {http://www.researchgate.net/publication/220469321_Automatic_Language_Classification_by_means_of_Syntactic_Dependency_Networks}, year = 2011 }
-
A. Mehler, K. Kühnberger, H. Lobin, H. Lüngen, A. Storrer, and A. Witt, Modeling, Learning and Processing of Text Technological Data Structures, A. Mehler, K. Kühnberger, H. Lobin, H. Lüngen, A. Storrer, and A. Witt, Eds., Berlin/New York: Springer, 2011.
[BibTeX]@Book{Mehler:Kuehnberger:Lobin:Luengen:Storrer:Witt:2011, Author = {Mehler, Alexander and Kühnberger, Kai-Uwe and Lobin, Henning and Lüngen, Harald and Storrer, Angelika and Witt, Andreas}, Editor = {Mehler, Alexander and Kühnberger, Kai-Uwe and Lobin, Henning and Lüngen, Harald and Storrer, Angelika and Witt, Andreas}, Title = {Modeling, Learning and Processing of Text Technological Data Structures}, Publisher = {Springer}, Series = {Studies in Computational Intelligence}, Address = {Berlin/New York}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/modelingLearningAndProcessing-medium.jpg}, pagetotal = {400}, website = {/books/texttechnologybook/}, year = 2011 }
-
U. Waltinger, On Social Semantics in Information Retrieval, Saarbrücken: Südwestdeutscher Verlag für Hochschulschriften, 2011. Zugl. Diss Univ. Bielefeld (2010)
[Abstract] [BibTeX]In this thesis we analyze the performance of social semantics in textual information retrieval. By means of collaboratively constructed knowledge derived from web-based social networks, inducing both common-sense and domain-specific knowledge as constructed by a multitude of users, we will establish an improvement in performance of selected tasks within different areas of information retrieval. This work connects the concepts and the methods of social networks and the semantic web to support the analysis of a social semantic web that combines human intelligence with machine learning and natural language processing. In this context, social networks, as instances of the social web, are capable in delivering social network data and document collections on a tremendous scale, inducing thematic dynamics that cannot be achieved by traditional expert resources. The question of an automatic conversion, annotation and processing, however, is central to the debate of the benefits of the social semantic web. Which kind of technologies and methods are available, adequate and contribute to the processing of this rapidly rising flood of information and at the same time being capable of using the wealth of information in this large, but more importantly decentralized internet. The present work researches the performance of social semantic-induced categorization by means of different document models. We will shed light on the question, to which level social networks and social ontologies contribute to selected areas within the information retrieval area, such as automatically determining term and text associations, identifying topics, text and web genre categorization, and also the domain of sentiment analysis. We will show in extensive evaluations, comparing the classical apparatus of text categorization -- Vector Space Model, Latent Semantic Analysis and Support Vector Maschine -- that significant improvements can be obtained by considering the collaborative knowledge derived from the social web.
@Book{Waltinger:2011, Author = {Waltinger, Ulli}, Title = {On Social Semantics in Information Retrieval}, Publisher = {Südwestdeutscher Verlag für Hochschulschriften}, Address = {Saarbrücken}, Note = {Zugl. Diss Univ. Bielefeld (2010)}, abstract = {In this thesis we analyze the performance of social semantics in textual information retrieval. By means of collaboratively constructed knowledge derived from web-based social networks, inducing both common-sense and domain-specific knowledge as constructed by a multitude of users, we will establish an improvement in performance of selected tasks within different areas of information retrieval. This work connects the concepts and the methods of social networks and the semantic web to support the analysis of a social semantic web that combines human intelligence with machine learning and natural language processing. In this context, social networks, as instances of the social web, are capable in delivering social network data and document collections on a tremendous scale, inducing thematic dynamics that cannot be achieved by traditional expert resources. The question of an automatic conversion, annotation and processing, however, is central to the debate of the benefits of the social semantic web. Which kind of technologies and methods are available, adequate and contribute to the processing of this rapidly rising flood of information and at the same time being capable of using the wealth of information in this large, but more importantly decentralized internet. The present work researches the performance of social semantic-induced categorization by means of different document models. We will shed light on the question, to which level social networks and social ontologies contribute to selected areas within the information retrieval area, such as automatically determining term and text associations, identifying topics, text and web genre categorization, and also the domain of sentiment analysis. We will show in extensive evaluations, comparing the classical apparatus of text categorization -- Vector Space Model, Latent Semantic Analysis and Support Vector Maschine -- that significant improvements can be obtained by considering the collaborative knowledge derived from the social web.}, pdf = {https://pub.uni-bielefeld.de/download/2302025/2302028}, website = {http://www.ulliwaltinger.de/on-social-semantics-in-information-retrieval/}, year = 2011 }
-
G. Doeben-Henisch, G. Abrami, M. Pfaff, and M. Struwe, “Conscious learning semiotics systems to assist human persons (CLS2H),” in AFRICON, 2011, 2011, pp. 1-7.
[Abstract] [BibTeX]Challenged by the growing societal demand for Ambient Assistive Living (AAL) technologies, we are dedicated to develop intelligent technical devices which are able to communicate with human persons in a truly human-like manner. The core of the project is a simulation environment which enables the development of conscious learning semiotic agents which will be able to assist human persons in their daily life. We are reporting first results and future perspectives.
@InProceedings{Doebenhenisch:Abrami:Pfaff:Struwe:2011, Author = {Doeben-Henisch, Gerd and Abrami, Giuseppe and Pfaff, Marcus and Struwe, Marvin}, Title = {Conscious learning semiotics systems to assist human persons (CLS2H)}, BookTitle = {AFRICON, 2011}, Volume = {}, Number = {}, Pages = {1 -7}, abstract = {Challenged by the growing societal demand for Ambient Assistive Living (AAL) technologies, we are dedicated to develop intelligent technical devices which are able to communicate with human persons in a truly human-like manner. The core of the project is a simulation environment which enables the development of conscious learning semiotic agents which will be able to assist human persons in their daily life. We are reporting first results and future perspectives.}, doi = {10.1109/AFRCON.2011.6072043}, issn = {2153-0025}, keywords = {ambient assistive living;conscious learning semiotic agents;conscious learning semiotics systems;human persons;intelligent technical devices;simulation environment;learning (artificial intelligence);multi-agent systems;}, month = {sept.}, pdf = {http://www.doeben-henisch.de/gdhnp/csg/africon2011.pdf}, website = {http://www.researchgate.net/publication/261451874_Conscious_Learning_Semiotics_Systems_to_Assist_Human_Persons_(CLS(2)H)}, year = 2011 }
-
U. Waltinger, A. Mehler, M. Lösch, and W. Horstmann, “Hierarchical Classification of OAI Metadata Using the DDC Taxonomy,” in Advanced Language Technologies for Digital Libraries (ALT4DL), R. Bernardi, S. Chambers, B. Gottfried, F. Segond, and I. Zaihrayeu, Eds., Berlin: Springer, 2011, pp. 29-40.
[Abstract] [BibTeX]In the area of digital library services, the access to subject-specific metadata of scholarly publications is of utmost interest. One of the most prevalent approaches for metadata exchange is the XML-based Open Archive Initiative (OAI) Protocol for Metadata Harvesting (OAI-PMH). However, due to its loose requirements regarding metadata content there is no strict standard for consistent subject indexing specified, which is furthermore needed in the digital library domain. This contribution addresses the problem of automatic enhancement of OAI metadata by means of the most widely used universal classification schemes in libraries—the Dewey Decimal Classification (DDC). To be more specific, we automatically classify scientific documents according to the DDC taxonomy within three levels using a machine learning-based classifier that relies solely on OAI metadata records as the document representation. The results show an asymmetric distribution of documents across the hierarchical structure of the DDC taxonomy and issues of data sparseness. However, the performance of the classifier shows promising results on all three levels of the DDC.
@InCollection{Waltinger:Mehler:Loesch:Horstmann:2011, Author = {Waltinger, Ulli and Mehler, Alexander and Lösch, Mathias and Horstmann, Wolfram}, Title = {Hierarchical Classification of OAI Metadata Using the DDC Taxonomy}, BookTitle = {Advanced Language Technologies for Digital Libraries (ALT4DL)}, Publisher = {Springer}, Editor = {Raffaella Bernardi and Sally Chambers and Bjoern Gottfried and Frederique Segond and Ilya Zaihrayeu}, Series = {LNCS}, Pages = {29-40}, Address = {Berlin}, abstract = {In the area of digital library services, the access to subject-specific metadata of scholarly publications is of utmost interest. One of the most prevalent approaches for metadata exchange is the XML-based Open Archive Initiative (OAI) Protocol for Metadata Harvesting (OAI-PMH). However, due to its loose requirements regarding metadata content there is no strict standard for consistent subject indexing specified, which is furthermore needed in the digital library domain. This contribution addresses the problem of automatic enhancement of OAI metadata by means of the most widely used universal classification schemes in libraries—the Dewey Decimal Classification (DDC). To be more specific, we automatically classify scientific documents according to the DDC taxonomy within three levels using a machine learning-based classifier that relies solely on OAI metadata records as the document representation. The results show an asymmetric distribution of documents across the hierarchical structure of the DDC taxonomy and issues of data sparseness. However, the performance of the classifier shows promising results on all three levels of the DDC.}, website = {http://www.springerlink.com/content/x20257512g818377/}, year = 2011 }
-
A. Mehler, S. Schwandt, R. Gleim, and B. Jussen, “Der eHumanities Desktop als Werkzeug in der historischen Semantik: Funktionsspektrum und Einsatzszenarien,” Journal for Language Technology and Computational Linguistics (JLCL), vol. 26, iss. 1, pp. 97-117, 2011.
[Abstract] [BibTeX]Die Digital Humanities bzw. die Computational Humanities entwickeln sich zu eigenständigen Disziplinen an der Nahtstelle von Geisteswissenschaft und Informatik. Diese Entwicklung betrifft zunehmend auch die Lehre im Bereich der geisteswissenschaftlichen Fachinformatik. In diesem Beitrag thematisieren wir den eHumanities Desktop als ein Werkzeug für diesen Bereich der Lehre. Dabei geht es genauer um einen Brückenschlag zwischen Geschichtswissenschaft und Informatik: Am Beispiel der historischen Semantik stellen wir drei Lehrszenarien vor, in denen der eHumanities Desktop in der geschichtswissenschaftlichen Lehre zum Einsatz kommt. Der Beitrag schliesst mit einer Anforderungsanalyse an zukünftige Entwicklungen in diesem Bereich.
@Article{Mehler:Schwandt:Gleim:Jussen:2011, Author = {Mehler, Alexander and Schwandt, Silke and Gleim, Rüdiger and Jussen, Bernhard}, Title = {Der eHumanities Desktop als Werkzeug in der historischen Semantik: Funktionsspektrum und Einsatzszenarien}, Journal = {Journal for Language Technology and Computational Linguistics (JLCL)}, Volume = {26}, Number = {1}, Pages = {97-117}, abstract = {Die Digital Humanities bzw. die Computational Humanities entwickeln sich zu eigenst{\"a}ndigen Disziplinen an der Nahtstelle von Geisteswissenschaft und Informatik. Diese Entwicklung betrifft zunehmend auch die Lehre im Bereich der geisteswissenschaftlichen Fachinformatik. In diesem Beitrag thematisieren wir den eHumanities Desktop als ein Werkzeug für diesen Bereich der Lehre. Dabei geht es genauer um einen Brückenschlag zwischen Geschichtswissenschaft und Informatik: Am Beispiel der historischen Semantik stellen wir drei Lehrszenarien vor, in denen der eHumanities Desktop in der geschichtswissenschaftlichen Lehre zum Einsatz kommt. Der Beitrag schliesst mit einer Anforderungsanalyse an zukünftige Entwicklungen in diesem Bereich.}, pdf = {http://media.dwds.de/jlcl/2011_Heft1/8.pdf }, year = 2011 }
-
T. Dong and T. vor der Brück, “Qualitative Spatial Knowledge Acquisition Based on the Connection Relation,” in Proceedings of the 3rd International Conference on Advanced Cognitive Technologies and Applications (COGNITIVE), Rome, Italy, 2011, pp. 70-75.
[Abstract] [BibTeX]Research in cognitive psychology shows that the connection relation is the primitive spatial relation. This paper proposes a novel spatial knowledge representation of indoor environments based on the connection relation, and demonstrates how deictic orientation relations can be acquired from a map, which is constructed purely on connection relations between extended objects. Without loss of generality, we restrict indoor environments to be constructed by a set of rectangles, each representing either a room or a corridor. The term fiat cell is coined to represent a subjective partition along a corridor. Spatial knowledge includes rectangles, sides information of rectangles, connection relations among rectangles, and fiat cells of rectangles. Efficient algorithms are given for identifying one shortest path between two locations, transforming paths into fiat paths, and acquiring deictic orientations.
@InProceedings{Dong:vor:der:Brueck:2011, Author = {Dong, Tiansi and vor der Brück, Tim}, Title = {Qualitative Spatial Knowledge Acquisition Based on the Connection Relation}, BookTitle = {Proceedings of the 3rd International Conference on Advanced Cognitive Technologies and Applications (COGNITIVE)}, Editor = {Terry Bossomaier and Pascal Lorenz}, Pages = {70--75}, Address = {Rome, Italy}, abstract = {Research in cognitive psychology shows that the connection relation is the primitive spatial relation. This paper proposes a novel spatial knowledge representation of indoor environments based on the connection relation, and demonstrates how deictic orientation relations can be acquired from a map, which is constructed purely on connection relations between extended objects. Without loss of generality, we restrict indoor environments to be constructed by a set of rectangles, each representing either a room or a corridor. The term fiat cell is coined to represent a subjective partition along a corridor. Spatial knowledge includes rectangles, sides information of rectangles, connection relations among rectangles, and fiat cells of rectangles. Efficient algorithms are given for identifying one shortest path between two locations, transforming paths into fiat paths, and acquiring deictic orientations.}, pdf = {http://www.thinkmind.org/download.php?articleid=cognitive_2011_3_40_40123}, website = {http://www.thinkmind.org/index.php?view=article&articleid=cognitive_2011_3_40_40123}, year = 2011 }
-
M. Z. Islam, R. Mittmann, and A. Mehler, “Multilingualism in Ancient Texts: Language Detection by Example of Old High German and Old Saxon,” in GSCL conference on Multilingual Resources and Multilingual Applications (GSCL 2011), 28-30 September, Hamburg, Germany, 2011.
[Abstract] [BibTeX]In this paper, we present an approach to language d etection in streams of multilingual ancient texts. We introduce a supervised classifier that detects, amongst others, Old High G erman (OHG) and Old Saxon (OS). We evaluate our mod el by means of three experiments that show that language detection is po ssible even for dead languages. Finally, we present an experiment in unsupervised language detection as a tertium comparationis for o ur supervised classifier.
@InProceedings{Zahurul:Mittmann:Mehler:2011, Author = {Islam, Md. Zahurul and Mittmann, Roland and Mehler, Alexander}, Title = {Multilingualism in Ancient Texts: Language Detection by Example of Old High German and Old Saxon}, BookTitle = {GSCL conference on Multilingual Resources and Multilingual Applications (GSCL 2011), 28-30 September, Hamburg, Germany}, abstract = {In this paper, we present an approach to language d etection in streams of multilingual ancient texts. We introduce a supervised classifier that detects, amongst others, Old High G erman (OHG) and Old Saxon (OS). We evaluate our mod el by means of three experiments that show that language detection is po ssible even for dead languages. Finally, we present an experiment in unsupervised language detection as a tertium comparationis for o ur supervised classifier.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Multilingualism_in_Ancient_Texts_Language_Detection_by_Example_of_Old_High_German_and_Old_Saxon.pdf}, timestamp = {2011.08.25}, year = 2011 }
2010 (26)
-
A. Mehler, “Minimum Spanning Markovian Trees: Introducing Context-Sensitivity into the Generation of Spanning Trees,” in Structural Analysis of Complex Networks, M. Dehmer, Ed., Basel: Birkhäuser Publishing, 2010, pp. 381-401.
[Abstract] [BibTeX]This chapter introduces a novel class of graphs: Minimum Spanning Markovian Trees (MSMTs). The idea behind MSMTs is to provide spanning trees that minimize the costs of edge traversals in a Markovian manner, that is, in terms of the path starting with the root of the tree and ending at the vertex under consideration. In a second part, the chapter generalizes this class of spanning trees in order to allow for damped Markovian effects in the course of spanning. These two effects, (1) the sensitivity to the contexts generated by consecutive edges and (2) the decreasing impact of more antecedent (or 'weakly remembered') vertices, are well known in cognitive modeling [6, 10, 21, 23]. In this sense, the chapter can also be read as an effort to introduce a graph model to support the simulation of cognitive systems. Note that MSMTs are not to be confused with branching Markov chains or Markov trees [20] as we focus on generating spanning trees from given weighted undirected networks.
@InCollection{Mehler:2010:a, Author = {Mehler, Alexander}, Title = {Minimum Spanning Markovian Trees: Introducing Context-Sensitivity into the Generation of Spanning Trees}, BookTitle = {Structural Analysis of Complex Networks}, Publisher = {Birkh{\"a}user Publishing}, Editor = {Dehmer, Matthias}, Pages = {381-401}, Address = {Basel}, abstract = {This chapter introduces a novel class of graphs: Minimum Spanning Markovian Trees (MSMTs). The idea behind MSMTs is to provide spanning trees that minimize the costs of edge traversals in a Markovian manner, that is, in terms of the path starting with the root of the tree and ending at the vertex under consideration. In a second part, the chapter generalizes this class of spanning trees in order to allow for damped Markovian effects in the course of spanning. These two effects, (1) the sensitivity to the contexts generated by consecutive edges and (2) the decreasing impact of more antecedent (or 'weakly remembered') vertices, are well known in cognitive modeling [6, 10, 21, 23]. In this sense, the chapter can also be read as an effort to introduce a graph model to support the simulation of cognitive systems. Note that MSMTs are not to be confused with branching Markov chains or Markov trees [20] as we focus on generating spanning trees from given weighted undirected networks.}, website = {https://www.researchgate.net/publication/226700676_Minimum_Spanning_Markovian_Trees_Introducing_Context-Sensitivity_into_the_Generation_of_Spanning_Trees}, year = 2010 }
-
R. Gleim and A. Mehler, “Computational Linguistics for Mere Mortals – Powerful but Easy-to-use Linguistic Processing for Scientists in the Humanities,” in Proceedings of LREC 2010, Malta, 2010.
[Abstract] [BibTeX]Delivering linguistic resources and easy-to-use methods to a broad public in the humanities is a challenging task. On the one hand users rightly demand easy to use interfaces but on the other hand want to have access to the full flexibility and power of the functions being offered. Even though a growing number of excellent systems exist which offer convenient means to use linguistic resources and methods, they usually focus on a specific domain, as for example corpus exploration or text categorization. Architectures which address a broad scope of applications are still rare. This article introduces the eHumanities Desktop, an online system for corpus management, processing and analysis which aims at bridging the gap between powerful command line tools and intuitive user interfaces.
@InProceedings{Gleim:Mehler:2010:b, Author = {Gleim, Rüdiger and Mehler, Alexander}, Title = {Computational Linguistics for Mere Mortals – Powerful but Easy-to-use Linguistic Processing for Scientists in the Humanities}, BookTitle = {Proceedings of LREC 2010}, Address = {Malta}, Publisher = {ELDA}, abstract = {Delivering linguistic resources and easy-to-use methods to a broad public in the humanities is a challenging task. On the one hand users rightly demand easy to use interfaces but on the other hand want to have access to the full flexibility and power of the functions being offered. Even though a growing number of excellent systems exist which offer convenient means to use linguistic resources and methods, they usually focus on a specific domain, as for example corpus exploration or text categorization. Architectures which address a broad scope of applications are still rare. This article introduces the eHumanities Desktop, an online system for corpus management, processing and analysis which aims at bridging the gap between powerful command line tools and intuitive user interfaces. }, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gleim_mehler_2010.pdf}, year = 2010 }
-
A. Mehler, A. Lücking, and P. Weiß, “A Network Model of Interpersonal Alignment,” Entropy, vol. 12, iss. 6, pp. 1440-1483, 2010.
[Abstract] [BibTeX]In dyadic communication, both interlocutors adapt to each other linguistically, that is, they align interpersonally. In this article, we develop a framework for modeling interpersonal alignment in terms of the structural similarity of the interlocutors’ dialog lexica. This is done by means of so-called two-layer time-aligned network series, that is, a time-adjusted graph model. The graph model is partitioned into two layers, so that the interlocutors’ lexica are captured as subgraphs of an encompassing dialog graph. Each constituent network of the series is updated utterance-wise. Thus, both the inherent bipartition of dyadic conversations and their gradual development are modeled. The notion of alignment is then operationalized within a quantitative model of structure formation based on the mutual information of the subgraphs that represent the interlocutor’s dialog lexica. By adapting and further developing several models of complex network theory, we show that dialog lexica evolve as a novel class of graphs that have not been considered before in the area of complex (linguistic) networks. Additionally, we show that our framework allows for classifying dialogs according to their alignment status. To the best of our knowledge, this is the first approach to measuring alignment in communication that explores the similarities of graph-like cognitive representations.
@Article{Mehler:Weiss:Luecking:2010:a, Author = {Mehler, Alexander and Lücking, Andy and Wei{\ss}, Petra}, Title = {A Network Model of Interpersonal Alignment}, Journal = {Entropy}, Volume = {12}, Number = {6}, Pages = {1440-1483}, abstract = {In dyadic communication, both interlocutors adapt to each other linguistically, that is, they align interpersonally. In this article, we develop a framework for modeling interpersonal alignment in terms of the structural similarity of the interlocutors’ dialog lexica. This is done by means of so-called two-layer time-aligned network series, that is, a time-adjusted graph model. The graph model is partitioned into two layers, so that the interlocutors’ lexica are captured as subgraphs of an encompassing dialog graph. Each constituent network of the series is updated utterance-wise. Thus, both the inherent bipartition of dyadic conversations and their gradual development are modeled. The notion of alignment is then operationalized within a quantitative model of structure formation based on the mutual information of the subgraphs that represent the interlocutor’s dialog lexica. By adapting and further developing several models of complex network theory, we show that dialog lexica evolve as a novel class of graphs that have not been considered before in the area of complex (linguistic) networks. Additionally, we show that our framework allows for classifying dialogs according to their alignment status. To the best of our knowledge, this is the first approach to measuring alignment in communication that explores the similarities of graph-like cognitive representations.}, doi = {10.3390/e12061440}, pdf = {http://www.mdpi.com/1099-4300/12/6/1440/pdf}, website = {http://www.mdpi.com/1099-4300/12/6/1440/}, year = 2010 }
-
A. Mehler, S. Sharoff, and M. Santini, Genres on the Web: Computational Models and Empirical Studies, A. Mehler, S. Sharoff, and M. Santini, Eds., Dordrecht: Springer, 2010.
[Abstract] [BibTeX]The volume 'Genres on the Web' has been designed for a wide audience, from the expert to the novice. It is a required book for scholars, researchers and students who want to become acquainted with the latest theoretical, empirical and computational advances in the expanding field of web genre research. The study of web genre is an overarching and interdisciplinary novel area of research that spans from corpus linguistics, computational linguistics, NLP, and text-technology, to web mining, webometrics, social network analysis and information studies. This book gives readers a thorough grounding in the latest research on web genres and emerging document types. The book covers a wide range of web-genre focussed subjects, such as: -The identification of the sources of web genres -Automatic web genre identification -The presentation of structure-oriented models -Empirical case studies One of the driving forces behind genre research is the idea of a genre-sensitive information system, which incorporates genre cues complementing the current keyword-based search and retrieval applications.
@Book{Mehler:Sharoff:Santini:2010:a, Author = {Mehler, Alexander and Sharoff, Serge and Santini, Marina}, Editor = {Mehler, Alexander and Sharoff, Serge and Santini, Marina}, Title = {Genres on the Web: Computational Models and Empirical Studies}, Publisher = {Springer}, Address = {Dordrecht}, abstract = {The volume 'Genres on the Web' has been designed for a wide audience, from the expert to the novice. It is a required book for scholars, researchers and students who want to become acquainted with the latest theoretical, empirical and computational advances in the expanding field of web genre research. The study of web genre is an overarching and interdisciplinary novel area of research that spans from corpus linguistics, computational linguistics, NLP, and text-technology, to web mining, webometrics, social network analysis and information studies. This book gives readers a thorough grounding in the latest research on web genres and emerging document types. The book covers a wide range of web-genre focussed subjects, such as: -The identification of the sources of web genres -Automatic web genre identification -The presentation of structure-oriented models -Empirical case studies One of the driving forces behind genre research is the idea of a genre-sensitive information system, which incorporates genre cues complementing the current keyword-based search and retrieval applications.}, booktitle = {Genres on the Web: Computational Models and Empirical Studies}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/GenresOnTheWeb.jpg}, pagetotal = {376}, review = {http://www.springerlink.com/content/ym07440380524721/}, website = {http://www.springer.com/computer/ai/book/978-90-481-9177-2}, year = 2010 }
-
T. Sutter and A. Mehler, Medienwandel als Wandel von Interaktionsformen – von frühen Medienkulturen zum Web 2.0, T. Sutter and A. Mehler, Eds., Wiesbaden: Verlag für Sozialwissenschaften, 2010.
[Abstract] [BibTeX]Die Beiträge des Bandes untersuchen den Medienwandel von frühen europäischen Medienkulturen bis zu aktuellen Formen der Internetkommunikation unter soziologischer, kulturwissenschaftlicher und linguistischer Perspektive. Zwar haben sich die Massenmedien von den Beschränkungen sozialer Interaktionen gelöst, sie weisen dem Publikum aber eine distanzierte, bloß rezipierende Rolle zu. Dagegen eröffnen neue Formen 'interaktiver' Medien gesteigerte Möglichkeiten der Rückmeldung und der Mitgestaltung für die Nutzer. Der vorliegende Band fragt nach der Qualität dieses Medienwandels: Werden Medien tatsächlich interaktiv? Was bedeutet die Interaktivität neuer Medien? Werden die durch neue Medien eröffneten Beteiligungsmöglichkeiten realisiert?
@Book{Sutter:Mehler:2010, Author = {Sutter, Tilmann and Mehler, Alexander}, Editor = {Sutter, Tilmann and Mehler, Alexander}, Title = {Medienwandel als Wandel von Interaktionsformen – von frühen Medienkulturen zum Web 2.0}, Publisher = {Verlag für Sozialwissenschaften}, Address = {Wiesbaden}, abstract = {Die Beitr{\"a}ge des Bandes untersuchen den Medienwandel von frühen europ{\"a}ischen Medienkulturen bis zu aktuellen Formen der Internetkommunikation unter soziologischer, kulturwissenschaftlicher und linguistischer Perspektive. Zwar haben sich die Massenmedien von den Beschr{\"a}nkungen sozialer Interaktionen gelöst, sie weisen dem Publikum aber eine distanzierte, blo{\ss} rezipierende Rolle zu. Dagegen eröffnen neue Formen 'interaktiver' Medien gesteigerte Möglichkeiten der Rückmeldung und der Mitgestaltung für die Nutzer. Der vorliegende Band fragt nach der Qualit{\"a}t dieses Medienwandels: Werden Medien tats{\"a}chlich interaktiv? Was bedeutet die Interaktivit{\"a}t neuer Medien? Werden die durch neue Medien eröffneten Beteiligungsmöglichkeiten realisiert?}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/Medienwandel.jpg}, pagetotal = {289}, website = {http://www.springer.com/de/book/9783531156422}, year = 2010 }
-
T. vor der Brück and H. Stenzhorn, “Logical Ontology Validation Using an Automatic Theorem Prover,” in Proceedings of the 19th European Conference on Artificial Intelligence (ECAI), Lisbon, Portugal, 2010, pp. 491-496.
[Abstract] [BibTeX]Ontologies are utilized for a wide range of tasks, like information retrieval/extraction or text generation, and in a multitude of domains, such as biology, medicine or business and commerce. To be actually usable in such real-world scenarios, ontologies usually have to encompass a large number of factual statements. However, with increasing size, it becomes very diffcult to ensure their complete correctness. This is particularly true in the case when an ontology is not hand-crafted but constructed (semi)automatically through text mining, for example. As a consequence, when inference mechanisms are applied on these ontologies, even minimal inconsistencies of tentimes lead to serious errors and are hard to trace back and find. This paper addresses this issue and describes a method to validate ontologies using an automatic theorem prover and MultiNet axioms. This logic-based approach allows to detect many inconsistencies, which are diffcult or even impossible to identify through statistical methods or by manual investigation in reasonable time. To make this approach accessible for ontology developers, a graphical user interface is provided that highlights erroneous axioms directly in the ontology for quicker fixing.
@InProceedings{vor:der:Brueck:Stenzhorn:2010, Author = {vor der Brück, Tim and Stenzhorn, Holger}, Title = {Logical Ontology Validation Using an Automatic Theorem Prover}, BookTitle = {Proceedings of the 19th European Conference on Artificial Intelligence (ECAI)}, Pages = {491--496}, Address = {Lisbon, Portugal}, abstract = {Ontologies are utilized for a wide range of tasks, like information retrieval/extraction or text generation, and in a multitude of domains, such as biology, medicine or business and commerce. To be actually usable in such real-world scenarios, ontologies usually have to encompass a large number of factual statements. However, with increasing size, it becomes very diffcult to ensure their complete correctness. This is particularly true in the case when an ontology is not hand-crafted but constructed (semi)automatically through text mining, for example. As a consequence, when inference mechanisms are applied on these ontologies, even minimal inconsistencies of tentimes lead to serious errors and are hard to trace back and find. This paper addresses this issue and describes a method to validate ontologies using an automatic theorem prover and MultiNet axioms. This logic-based approach allows to detect many inconsistencies, which are diffcult or even impossible to identify through statistical methods or by manual investigation in reasonable time. To make this approach accessible for ontology developers, a graphical user interface is provided that highlights erroneous axioms directly in the ontology for quicker fixing.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/ECAI-216.pdf}, year = 2010 }
-
T. vor der Brück, “Hypernymy Extraction Using a Semantic Network Representation,” International Journal of Computational Linguistics and Applications, vol. 1, iss. 1, pp. 105-119, 2010.
[Abstract] [BibTeX]There are several approaches to detect hypernymy relations from texts by text mining. Usually these approaches are based on supervised learning and in a first step are extracting several patterns. These patterns are then applied to previously unseen texts and used to recognize hypernym/hyponym pairs. Normally these approaches are only based on a surface representation or a syntactical tree structure, i.e., constituency or dependency trees derived by a syntactical parser. In this work, however, we present an approach that operates directly on a semantic network (SN), which is generated by a deep syntactico-semantic analysis. Hyponym/hypernym pairs are then extracted by the application of graph matching. This algorithm is combined with a shallow approach enriched with semantic information.
@Article{vor:der:Brueck:2010, Author = {vor der Brück, Tim}, Title = {Hypernymy Extraction Using a Semantic Network Representation}, Journal = {International Journal of Computational Linguistics and Applications}, Volume = {1}, Number = {1}, Pages = {105--119}, abstract = {There are several approaches to detect hypernymy relations from texts by text mining. Usually these approaches are based on supervised learning and in a first step are extracting several patterns. These patterns are then applied to previously unseen texts and used to recognize hypernym/hyponym pairs. Normally these approaches are only based on a surface representation or a syntactical tree structure, i.e., constituency or dependency trees derived by a syntactical parser. In this work, however, we present an approach that operates directly on a semantic network (SN), which is generated by a deep syntactico-semantic analysis. Hyponym/hypernym pairs are then extracted by the application of graph matching. This algorithm is combined with a shallow approach enriched with semantic information.}, pdf = {http://www.gelbukh.com/ijcla/2010-1-2/Hypernymy Extraction Using.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.358.533}, year = 2010 }
-
T. vor der Brück, “Learning Deep Semantic Patterns for Hypernymy Extraction Following the Minimum Description Length Principle,” in Proceedings of the 29th International Conference on Lexis and Grammar (LGC), Belgrade, Serbia, 2010, pp. 39-49.
[Abstract] [BibTeX]Current approaches of hypernymy acquisition are mostly based on syntactic or surface representations and extract hypernymy relations between surface word forms and not word readings. In this paper we present a purely semantic approach for hypernymy extraction based on semantic networks (SNs). This approach employs a set of patterns sub0 (a1,a2) <-- premise where the premise part of a pattern is given by a SN. Furthermore this paper describes how the patterns can be derived by relational statistical learning following the Minimum Description Length principle (MDL). The evaluation demonstrates the usefulness of the learned patterns and also of the entire hypernymy extraction system.
@InProceedings{vor:der:Brueck:2010:a, Author = {vor der Brück, Tim}, Title = {Learning Deep Semantic Patterns for Hypernymy Extraction Following the Minimum Description Length Principle}, BookTitle = {Proceedings of the 29th International Conference on Lexis and Grammar (LGC)}, Pages = {39--49}, Address = {Belgrade, Serbia}, abstract = {Current approaches of hypernymy acquisition are mostly based on syntactic or surface representations and extract hypernymy relations between surface word forms and not word readings. In this paper we present a purely semantic approach for hypernymy extraction based on semantic networks (SNs). This approach employs a set of patterns sub0 (a1,a2) <-- premise where the premise part of a pattern is given by a SN. Furthermore this paper describes how the patterns can be derived by relational statistical learning following the Minimum Description Length principle (MDL). The evaluation demonstrates the usefulness of the learned patterns and also of the entire hypernymy extraction system.}, year = 2010 }
-
T. vor der Brück, "Learning Semantic Network Patterns for Hypernymy Extraction," in Proceedings of the 6th Workshop on Ontologies and Lexical Resources (OntoLex), Beijing, China, 2010, pp. 38-47.
[BibTeX]@InProceedings{vor:der:Brueck:2010:b, Author = {vor der Brück, Tim}, Title = {Learning Semantic Network Patterns for Hypernymy Extraction}, BookTitle = {Proceedings of the 6th Workshop on Ontologies and Lexical Resources (OntoLex)}, Pages = {38--47}, Address = {Beijing, China}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/ontolex_brueck_13_2010.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.358.533}, year = 2010 }
-
S. Hartrumpf, T. vor der Brück, and C. Eichhorn, "Detecting Duplicates with Shallow and Parser-based Methods," in Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering (NLPKE), Beijing, China, 2010, pp. 142-149.
[Abstract] [BibTeX]Identifying duplicate texts is important in many areas like plagiarism detection, information retrieval, text summarization, and question answering. Current approaches are mostly surface-oriented (or use only shallow syntactic representations) and see each text only as a token list. In this work however, we describe a deep, semantically oriented method based on semantic networks which are derived by a syntactico-semantic parser. Semantically identical or similar semantic networks for each sentence of a given base text are efficiently retrieved by using a specialized semantic network index. In order to detect many kinds of paraphrases the current base semantic network is varied by applying inferences: lexico-semantic relations, relation axioms, and meaning postulates. Some important phenomena occurring in difficult-to-detect duplicates are discussed. The deep approach profits from background knowledge, whose acquisition from corpora like Wikipedia is explained briefly. This deep duplicate recognizer is combined with two shallow duplicate recognizers in order to guarantee high recall for texts which are not fully parsable. The evaluation shows that the combined approach preserves recall and increases precision considerably, in comparison to traditional shallow methods. For the evaluation, a standard corpus of German plagiarisms was extended by four diverse components with an emphasis on duplicates (and not just plagiarisms), e.g., news feed articles from different web sources and two translations of the same short story.
@InProceedings{vor:der:Brueck:Hartrumpf:Eichhorn:2010:a, Author = {Hartrumpf, Sven and vor der Brück, Tim and Eichhorn, Christian}, Title = {Detecting Duplicates with Shallow and Parser-based Methods}, BookTitle = {Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering (NLPKE)}, Pages = {142--149}, Address = {Beijing, China}, abstract = {Identifying duplicate texts is important in many areas like plagiarism detection, information retrieval, text summarization, and question answering. Current approaches are mostly surface-oriented (or use only shallow syntactic representations) and see each text only as a token list. In this work however, we describe a deep, semantically oriented method based on semantic networks which are derived by a syntactico-semantic parser. Semantically identical or similar semantic networks for each sentence of a given base text are efficiently retrieved by using a specialized semantic network index. In order to detect many kinds of paraphrases the current base semantic network is varied by applying inferences: lexico-semantic relations, relation axioms, and meaning postulates. Some important phenomena occurring in difficult-to-detect duplicates are discussed. The deep approach profits from background knowledge, whose acquisition from corpora like Wikipedia is explained briefly. This deep duplicate recognizer is combined with two shallow duplicate recognizers in order to guarantee high recall for texts which are not fully parsable. The evaluation shows that the combined approach preserves recall and increases precision considerably, in comparison to traditional shallow methods. For the evaluation, a standard corpus of German plagiarisms was extended by four diverse components with an emphasis on duplicates (and not just plagiarisms), e.g., news feed articles from different web sources and two translations of the same short story.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/semdupl-ieee.pdf}, website = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5587838&abstractAccess=no&userType=inst}, year = 2010 }
-
S. Hartrumpf, T. vor der Brück, and C. Eichhorn, "Semantic Duplicate Identification with Parsing and Machine Learning," in Proceedings of the 13th International Conference on Text, Speech and Dialogue (TSD 2010), Brno, Czech Republic, 2010, pp. 84-92.
[Abstract] [BibTeX]Identifying duplicate texts is important in many areas like plagiarism detection, information retrieval, text summarization, and question answering. Current approaches are mostly surface-oriented (or use only shallow syntactic representations) and see each text only as a token list. In this work however, we describe a deep, semantically oriented method based on semantic networks which are derived by a syntacticosemantic parser. Semantically identical or similar semantic networks for each sentence of a given base text are efficiently retrieved by using a specialized index. In order to detect many kinds of paraphrases the semantic networks of a candidate text are varied by applying inferences: lexico- semantic relations, relation axioms, and meaning postulates. Important phenomena occurring in difficult duplicates are discussed. The deep approach profits from background knowledge, whose acquisition from corpora is explained briefly. The deep duplicate recognizer is combined with two shallow duplicate recognizers in order to guarantee a high recall for texts which are not fully parsable. The evaluation shows that the combined approach preserves recall and increases precision considerably in comparison to traditional shallow methods.
@InProceedings{vor:der:Brueck:Hartrumpf:Eichhorn:2010:b, Author = {Hartrumpf, Sven and vor der Brück, Tim and Eichhorn, Christian}, Title = {Semantic Duplicate Identification with Parsing and Machine Learning}, BookTitle = {Proceedings of the 13th International Conference on Text, Speech and Dialogue (TSD 2010)}, Editor = {Petr Sojka and Aleš Horák and Ivan Kopeček and Karel Pala}, Volume = {6231}, Series = {Lecture Notes in Artificial Intelligence}, Pages = {84--92}, Address = {Brno, Czech Republic}, abstract = {Identifying duplicate texts is important in many areas like plagiarism detection, information retrieval, text summarization, and question answering. Current approaches are mostly surface-oriented (or use only shallow syntactic representations) and see each text only as a token list. In this work however, we describe a deep, semantically oriented method based on semantic networks which are derived by a syntacticosemantic parser. Semantically identical or similar semantic networks for each sentence of a given base text are efficiently retrieved by using a specialized index. In order to detect many kinds of paraphrases the semantic networks of a candidate text are varied by applying inferences: lexico- semantic relations, relation axioms, and meaning postulates. Important phenomena occurring in difficult duplicates are discussed. The deep approach profits from background knowledge, whose acquisition from corpora is explained briefly. The deep duplicate recognizer is combined with two shallow duplicate recognizers in order to guarantee a high recall for texts which are not fully parsable. The evaluation shows that the combined approach preserves recall and increases precision considerably in comparison to traditional shallow methods.}, month = {September}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/semdupl-paper.pdf}, website = {http://link.springer.com/chapter/10.1007/978-3-642-15760-8_12}, year = 2010 }
-
T. vor der Brück and H. Helbig, "Retrieving Meronyms from Texts Using An Automated Theorem Prover," Journal for Language Technology and Computational Linguistics (JLCL), vol. 25, iss. 1, pp. 57-81, 2010.
[Abstract] [BibTeX]In this paper we present a truly semantic-oriented approach for meronymy relation extraction. It directly operates, instead of syntactic trees or surface representations, on semantic networks (SNs). These SNs are derived from texts (in our case, the German Wikip edia) by a deep linguistic syntactico-semantic analysis. The extraction of meronym/holonym pairs is carried out by using, among other components, an automated theorem prover, whose work is based on a set of logical axioms. The corresponding algorithm is combined with a shallow approach enriched with semantic information. Through the employment of logical methods, the recall and precision of the semantic patterns pertinent to the extracted relations can be increased considerably.
@Article{vor:der:Brueck:Helbig:2010:b, Author = {vor der Brück, Tim and Helbig, Hermann}, Title = {Retrieving Meronyms from Texts Using An Automated Theorem Prover}, Journal = {Journal for Language Technology and Computational Linguistics (JLCL)}, Volume = {25}, Number = {1}, Pages = {57--81}, abstract = {In this paper we present a truly semantic-oriented approach for meronymy relation extraction. It directly operates, instead of syntactic trees or surface representations, on semantic networks (SNs). These SNs are derived from texts (in our case, the German Wikip edia) by a deep linguistic syntactico-semantic analysis. The extraction of meronym/holonym pairs is carried out by using, among other components, an automated theorem prover, whose work is based on a set of logical axioms. The corresponding algorithm is combined with a shallow approach enriched with semantic information. Through the employment of logical methods, the recall and precision of the semantic patterns pertinent to the extracted relations can be increased considerably.}, pdf = {http://www.jlcl.org/2010_Heft1/tim_vorderbrueck.pdf}, year = 2010 }
-
A. Lücking and K. Bergmann, Introducing the Bielefeld SaGA CorpusEuropa Universität Viadrina Frankfurt/Oder: , 2010.
[Abstract] [BibTeX]People communicate multimodally. Most prominently, they co-produce speech and gesture. How do they do that? Studying the interplay of both modalities has to be informed by empirically observed communication behavior. We present a corpus built of speech and gesture data gained in a controlled study. We describe 1) the setting underlying the data; 2) annotation of the data; 3) reliability evalution methods and results; and 4) applications of the corpus in the research domain of speech and gesture alignment.
@Misc{Luecking:Bergmann:2010, Author = {Andy L\"{u}cking and Kirsten Bergmann}, Title = {Introducing the {B}ielefeld {SaGA} Corpus}, HowPublished = {Talk given at \textit{Gesture: Evolution, Brain, and Linguistic Structures.} 4th Conference of the International Society for Gesture Studies (ISGS). Europa Universit\"{a}t Viadrina Frankfurt/Oder}, abstract = {People communicate multimodally. Most prominently, they co-produce speech and gesture. How do they do that? Studying the interplay of both modalities has to be informed by empirically observed communication behavior. We present a corpus built of speech and gesture data gained in a controlled study. We describe 1) the setting underlying the data; 2) annotation of the data; 3) reliability evalution methods and results; and 4) applications of the corpus in the research domain of speech and gesture alignment.}, address = {Europa Universit{\"a}t Viadrina Frankfurt/Oder}, day = {28}, month = {07}, year = 2010 }
-
A. Lücking, "A Semantic Account for Iconic Gestures," in Gesture: Evolution, Brain, and Linguistic Structures, Europa Universität Viadrina Frankfurt/Oder, 2010, p. 210.
[BibTeX]@InProceedings{Luecking:2010, Author = {Lücking, Andy}, Title = {A Semantic Account for Iconic Gestures}, BookTitle = {Gesture: Evolution, Brain, and Linguistic Structures}, Pages = {210}, Address = {Europa Universit{\"a}t Viadrina Frankfurt/Oder}, Organization = {4th Conference of the International Society for Gesture Studies (ISGS)}, keywords = {own}, month = {7}, pdf = {https://pub.uni-bielefeld.de/download/2318565/2319962}, website = {http://pub.uni-bielefeld.de/publication/2318565}, year = 2010 }
-
A. Lücking, K. Bergmann, F. Hahn, S. Kopp, and H. Rieser, "The Bielefeld Speech and Gesture Alignment Corpus (SaGA)," in Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality, Malta, 2010, pp. 92-98.
[Abstract] [BibTeX]People communicate multimodally. Most prominently, they co-produce speech and gesture. How do they do that? Studying the interplay of both modalities has to be informed by empirically observed communication behavior. We present a corpus built of speech and gesture data gained in a controlled study. We describe 1) the setting underlying the data; 2) annotation of the data; 3) reliability evalution methods and results; and 4) applications of the corpus in the research domain of speech and gesture alignment.
@InProceedings{Luecking:et:al:2010, Author = {Lücking, Andy and Bergmann, Kirsten and Hahn, Florian and Kopp, Stefan and Rieser, Hannes}, Title = {The Bielefeld Speech and Gesture Alignment Corpus (SaGA)}, BookTitle = {Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality}, Pages = {92--98}, Address = {Malta}, Organization = {7th International Conference for Language Resources and Evaluation (LREC 2010)}, abstract = {People communicate multimodally. Most prominently, they co-produce speech and gesture. How do they do that? Studying the interplay of both modalities has to be informed by empirically observed communication behavior. We present a corpus built of speech and gesture data gained in a controlled study. We describe 1) the setting underlying the data; 2) annotation of the data; 3) reliability evalution methods and results; and 4) applications of the corpus in the research domain of speech and gesture alignment.}, keywords = {own}, month = {5}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/saga-corpus.pdf}, website = {http://pub.uni-bielefeld.de/publication/2001935}, year = 2010 }
-
M. Z. Islam, J. Tiedemann, and A. Eisele, "English to Bangla Phrase – Based Machine Translation," in The 14th Annual Conference of The European Association for Machine Translation. Saint-Raphaël, France, 27-28 May, 2010.
[BibTeX]@InProceedings{Zahurul:Tiedemann:Eisele:2010, Author = {Islam, Md. Zahurul and Tiedemann, Jörg and Eisele, Andreas}, Title = {English to Bangla Phrase – Based Machine Translation}, BookTitle = {The 14th Annual Conference of The European Association for Machine Translation. Saint-Raphaël, France, 27-28 May}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/English_to_Bangla_Phrase–Based_Machine_Translation.pdf}, timestamp = {2011.08.02}, year = 2010 }
-
U. Waltinger, "GermanPolarityClues: A Lexical Resource for German Sentiment Analysis," in Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC '10), Valletta, Malta, 2010.
[BibTeX]@InProceedings{Waltinger:2010:a, Author = {Waltinger, Ulli}, Title = {GermanPolarityClues: A Lexical Resource for German Sentiment Analysis}, BookTitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC '10)}, Editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, Address = {Valletta, Malta}, Publisher = {European Language Resources Association (ELRA)}, date_0 = {2010-05}, isbn = {2-9517408-6-7}, language = {english}, month = {may}, pdf = {http://www.ulliwaltinger.de/pdf/91_Paper.pdf}, website = {http://www.ulliwaltinger.de/sentiment/}, year = 2010 }
-
U. Waltinger, "GermanPolarityClues: A Lexical Resource for German Sentiment Analysis," in Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC '10), Valletta, Malta, 2010.
[BibTeX]@InProceedings{Waltinger:2010:b, Author = {Waltinger, Ulli}, Title = {GermanPolarityClues: A Lexical Resource for German Sentiment Analysis}, BookTitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC '10)}, Editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, Address = {Valletta, Malta}, Publisher = {European Language Resources Association (ELRA)}, date_0 = {2010-05}, isbn = {2-9517408-6-7}, language = {english}, month = {may}, year = 2010 }
-
A. Mehler, P. Weiß, P. Menke, and A. Lücking, "Towards a Simulation Model of Dialogical Alignment," in Proceedings of the 8th International Conference on the Evolution of Language (Evolang8), 14-17 April 2010, Utrecht, 2010, pp. 238-245.
[BibTeX]@InProceedings{Mehler:Weiss:Menke:Luecking:2010, Author = {Mehler, Alexander and Wei{\ss}, Petra and Menke, Peter and Lücking, Andy}, Title = {Towards a Simulation Model of Dialogical Alignment}, BookTitle = {Proceedings of the 8th International Conference on the Evolution of Language (Evolang8), 14-17 April 2010, Utrecht}, Pages = {238-245}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Alexander_Mehler_Petra_Weiss_Peter_Menke_Andy_Luecking.pdf}, website = {http://www.let.uu.nl/evolang2010.nl/}, year = 2010 }
-
F. Foscarini, Y. Kim, C. A. Lee, A. Mehler, G. Oliver, and S. Ross, "On the Notion of Genre in Digital Preservation," in Automation in Digital Preservation, Dagstuhl, Germany, 2010.
[BibTeX]@InProceedings{Foscarini:Kim:Lee:Mehler:Oliver:Ross:2010, Author = {Foscarini, Fiorella and Kim, Yunhyong and Lee, Christopher A. and Mehler, Alexander and Oliver, Gillian and Ross, Seamus}, Title = {On the Notion of Genre in Digital Preservation}, BookTitle = {Automation in Digital Preservation}, Editor = {Chanod, Jean-Pierre and Dobreva, Milena and Rauber, Andreas and Ross, Seamus}, Number = {10291}, Series = {Dagstuhl Seminar Proceedings}, Address = {Dagstuhl, Germany}, Publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany}, annote = {Keywords: Digital preservation, genre analysis, context modeling, diplomatics, information retrieval}, issn = {1862-4405}, pdf = {http://drops.dagstuhl.de/opus/volltexte/2010/2763/pdf/10291.MehlerAlexander.Paper.2763.pdf}, website = {http://drops.dagstuhl.de/opus/volltexte/2010/2763}, year = 2010 }
-
A. Mehler, R. Gleim, U. Waltinger, and N. Diewald, "Time Series of Linguistic Networks by Example of the Patrologia Latina," in Proceedings of INFORMATIK 2010: Service Science, September 27 - October 01, 2010, Leipzig, 2010, pp. 609-616.
[BibTeX]@InProceedings{Mehler:Gleim:Waltinger:Diewald:2010, Author = {Mehler, Alexander and Gleim, Rüdiger and Waltinger, Ulli and Diewald, Nils}, Title = {Time Series of Linguistic Networks by Example of the Patrologia Latina}, BookTitle = {Proceedings of INFORMATIK 2010: Service Science, September 27 - October 01, 2010, Leipzig}, Editor = {F{\"a}hnrich, Klaus-Peter and Franczyk, Bogdan}, Volume = {2}, Series = {Lecture Notes in Informatics}, Pages = {609-616}, Publisher = {GI}, pdf = {http://subs.emis.de/LNI/Proceedings/Proceedings176/586.pdf}, year = 2010 }
-
R. Gleim, P. Warner, and A. Mehler, "eHumanities Desktop - An Architecture for Flexible Annotation in Iconographic Research," in Proceedings of the 6th International Conference on Web Information Systems and Technologies (WEBIST '10), April 7-10, 2010, Valencia, 2010.
[BibTeX]@InProceedings{Gleim:Warner:Mehler:2010, Author = {Gleim, Rüdiger and Warner, Paul and Mehler, Alexander}, Title = {eHumanities Desktop - An Architecture for Flexible Annotation in Iconographic Research}, BookTitle = {Proceedings of the 6th International Conference on Web Information Systems and Technologies (WEBIST '10), April 7-10, 2010, Valencia}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gleim_warner_mehler_2010.pdf}, website = {https://www.researchgate.net/publication/220724277_eHumanities_Desktop_-_An_Architecture_for_Flexible_Annotation_in_Iconographic_Research}, year = 2010 }
-
P. Menke and A. Mehler, "The Ariadne System: A flexible and extensible framework for the modeling and storage of experimental data in the humanities," in Proceedings of LREC 2010, Malta, 2010.
[Abstract] [BibTeX]This paper introduces the Ariadne Corpus Management System. First, the underlying data model is presented which enables users to represent and process heterogeneous data sets within a single, consistent framework. Secondly, a set of automatized procedures is described that offers assistance to researchers in various data-related use cases. Finally, an approach to easy yet powerful data retrieval is introduced in form of a specialised querying language for multimodal data.
@InProceedings{Menke:Mehler:2010, Author = {Menke, Peter and Mehler, Alexander}, Title = {The Ariadne System: A flexible and extensible framework for the modeling and storage of experimental data in the humanities}, BookTitle = {Proceedings of LREC 2010}, Address = {Malta}, Publisher = {ELDA}, abstract = {This paper introduces the Ariadne Corpus Management System. First, the underlying data model is presented which enables users to represent and process heterogeneous data sets within a single, consistent framework. Secondly, a set of automatized procedures is described that offers assistance to researchers in various data-related use cases. Finally, an approach to easy yet powerful data retrieval is introduced in form of a specialised querying language for multimodal data.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/menke_mehler_2010.pdf}, website = {http://arnetminer.org/publication/the-ariadne-system-a-flexible-and-extensible-framework-for-the-modeling-and-storage-of-experimental-data-in-the-humanities-2839925.html}, year = 2010 }
-
T. Sutter and A. Mehler, "Einleitung: Der aktuelle Medienwandel im Blick einer interdisziplinären Medienwissenschaft," in Medienwandel als Wandel von Interaktionsformen, T. Sutter and A. Mehler, Eds., Wiesbaden: VS Verlag für Sozialwissenschaften, 2010, pp. 7-16.
[Abstract] [BibTeX]Die Herausforderung, die der Wandel von Kommunikationsmedien für die Medienwissenschaft darstellt, resultiert nicht nur aus der ungeheuren Beschleunigung des Medienwandels. Die Herausforderung stellt sich auch mit der Frage, welches die neuen Formen und Strukturen sind, die aus dem Wandel der Medien hervorgehen. Rückt man diese Frage in den Fokus der Überlegungen, kommen erstens Entwicklungen im Wechsel von Massenmedien zu neuen, „interaktiven`` Medien in den Blick. Dies betrifft den Wandel von den alten Medien in Form von Einwegkommunikation zu den neuen Medien in Form von Netzkommunikation. Dieser Wandel wurde in zahlreichen Analysen als eine Revolution beschrieben: Im Unterschied zur einseitigen, rückkopplungsarmen Kommunikationsform der Massenmedien sollen neue, computergestützte Formen der Medienkommunikation „interaktiv`` sein, d.h. gesteigerte Rückkopplungs- und Eingriffsmöglichkeiten für die Adressaten und Nutzer bieten. Sozialwissenschaftlich bedeutsam ist dabei die Einschätzung der Qualität und des Umfangs dieser neuen Möglichkeiten und Leistungen. Denn bislang bedeutete Medienwandel im Kern eine zunehmende Ausdifferenzierung alter und neuer Medien mit je spezifischen Leistungen, d.h. neue Medien ersetzen die älteren nicht, sondern sie ergänzen und erweitern sie. Allerdings wird im Zuge des aktuellen Medienwandels immer deutlicher, dass die neuen Medien durchaus imstande sind, die Leistungen massenmedialer Verbreitung von Kommunikation zu übernehmen. Stehen wir also, wie das schon seit längerem kühn vorhergesagt wird, vor der Etablierung eines Universalmediums, das in der Lage ist, die Formen und Funktionen anderer Medien zu übernehmen?
@InBook{Sutter2010, Author = {Sutter, Tilmann and Mehler, Alexander}, Editor = {Sutter, Tilmann and Mehler, Alexander}, Title = {Einleitung: Der aktuelle Medienwandel im Blick einer interdisziplin{\"a}ren Medienwissenschaft}, Pages = {7--16}, Publisher = {VS Verlag f{\"u}r Sozialwissenschaften}, Address = {Wiesbaden}, abstract = {Die Herausforderung, die der Wandel von Kommunikationsmedien f{\"u}r die Medienwissenschaft darstellt, resultiert nicht nur aus der ungeheuren Beschleunigung des Medienwandels. Die Herausforderung stellt sich auch mit der Frage, welches die neuen Formen und Strukturen sind, die aus dem Wandel der Medien hervorgehen. R{\"u}ckt man diese Frage in den Fokus der {\"U}berlegungen, kommen erstens Entwicklungen im Wechsel von Massenmedien zu neuen, „interaktiven`` Medien in den Blick. Dies betrifft den Wandel von den alten Medien in Form von Einwegkommunikation zu den neuen Medien in Form von Netzkommunikation. Dieser Wandel wurde in zahlreichen Analysen als eine Revolution beschrieben: Im Unterschied zur einseitigen, r{\"u}ckkopplungsarmen Kommunikationsform der Massenmedien sollen neue, computergest{\"u}tzte Formen der Medienkommunikation „interaktiv`` sein, d.h. gesteigerte R{\"u}ckkopplungs- und Eingriffsm{\"o}glichkeiten f{\"u}r die Adressaten und Nutzer bieten. Sozialwissenschaftlich bedeutsam ist dabei die Einsch{\"a}tzung der Qualit{\"a}t und des Umfangs dieser neuen M{\"o}glichkeiten und Leistungen. Denn bislang bedeutete Medienwandel im Kern eine zunehmende Ausdifferenzierung alter und neuer Medien mit je spezifischen Leistungen, d.h. neue Medien ersetzen die {\"a}lteren nicht, sondern sie erg{\"a}nzen und erweitern sie. Allerdings wird im Zuge des aktuellen Medienwandels immer deutlicher, dass die neuen Medien durchaus imstande sind, die Leistungen massenmedialer Verbreitung von Kommunikation zu {\"u}bernehmen. Stehen wir also, wie das schon seit l{\"a}ngerem k{\"u}hn vorhergesagt wird, vor der Etablierung eines Universalmediums, das in der Lage ist, die Formen und Funktionen anderer Medien zu {\"u}bernehmen?}, booktitle = {Medienwandel als Wandel von Interaktionsformen}, doi = {10.1007/978-3-531-92292-8_1}, isbn = {978-3-531-92292-8}, url = {https://doi.org/10.1007/978-3-531-92292-8_1}, year = 2010 }
-
S. Eger and I. Sejane, "Computing Semantic Similarity from Bilingual Dictionaries," in Proceedings of the 10th International Conference on the Statistical Analysis of Textual Data (JADT-2010), Rome, Italy, 2010, pp. 1217-1225.
[BibTeX]@InProceedings{Eger:Sejane:2010, Author = {Eger, Steffen and Sejane, Ineta}, Title = {Computing Semantic Similarity from Bilingual Dictionaries}, BookTitle = {Proceedings of the 10th International Conference on the Statistical Analysis of Textual Data (JADT-2010)}, Pages = {1217-1225}, Address = {Rome, Italy}, Publisher = {JADT-2010}, pdf = {http://www.ledonline.it/ledonline/JADT-2010/allegati/JADT-2010-1217-1226_167-Eger.pdf}, year = 2010 }
-
T. vor der Brück and H. Helbig, "Validating Meronymy Hypotheses with Support Vector Machines and Graph Kernels," in Proceedings of the Ninth International Conference on Machine Learning and Applications (ICMLA), Washington, D.C., 2010, pp. 243-250.
[Abstract] [BibTeX]There is a substantial body of work on the extraction of relations from texts, most of which is based on pattern matching or on applying tree kernel functions to syntactic structures. Whereas pattern application is usually more efficient, tree kernels can be superior when assessed by the F-measure. In this paper, we introduce a hybrid approach to extracting meronymy relations, which is based on both patterns and kernel functions. In a first step, meronymy relation hypotheses are extracted from a text corpus by applying patterns. In a second step these relation hypotheses are validated by using several shallow features and a graph kernel approach. In contrast to other meronymy extraction and validation methods which are based on surface or syntactic representations we use a purely semantic approach based on semantic networks. This involves analyzing each sentence of the Wikipedia corpus by a deep syntactico-semantic parser and converting it into a semantic network. Meronymy relation hypotheses are extracted from the semantic networks by means of an automated theorem prover, which employs a set of logical axioms and patterns in the form of semantic networks. The meronymy candidates are then validated by means of a graph kernel approach based on common walks. The evaluation shows that this method achieves considerably higher accuracy, recall, and F-measure than a method using purely shallow validation.
@InProceedings{vor:der:Brueck:Helbig:2010:a, Author = {vor der Brück, Tim and Helbig, Hermann}, Title = {Validating Meronymy Hypotheses with Support Vector Machines and Graph Kernels}, BookTitle = {Proceedings of the Ninth International Conference on Machine Learning and Applications (ICMLA)}, Pages = {243--250}, Address = {Washington, D.C.}, Publisher = {IEEE Press}, abstract = {There is a substantial body of work on the extraction of relations from texts, most of which is based on pattern matching or on applying tree kernel functions to syntactic structures. Whereas pattern application is usually more efficient, tree kernels can be superior when assessed by the F-measure. In this paper, we introduce a hybrid approach to extracting meronymy relations, which is based on both patterns and kernel functions. In a first step, meronymy relation hypotheses are extracted from a text corpus by applying patterns. In a second step these relation hypotheses are validated by using several shallow features and a graph kernel approach. In contrast to other meronymy extraction and validation methods which are based on surface or syntactic representations we use a purely semantic approach based on semantic networks. This involves analyzing each sentence of the Wikipedia corpus by a deep syntactico-semantic parser and converting it into a semantic network. Meronymy relation hypotheses are extracted from the semantic networks by means of an automated theorem prover, which employs a set of logical axioms and patterns in the form of semantic networks. The meronymy candidates are then validated by means of a graph kernel approach based on common walks. The evaluation shows that this method achieves considerably higher accuracy, recall, and F-measure than a method using purely shallow validation.}, website = {http://www.computer.org/csdl/proceedings/icmla/2010/4300/00/4300a243-abs.html}, year = 2010 }
2009 (23)
-
M. Santini, A. Mehler, and S. Sharoff, "Riding the Rough Waves of Genre on the Web: Concepts and Research Questions," in Genres on the Web: Computational Models and Empirical Studies, A. Mehler, S. Sharoff, and M. Santini, Eds., Berlin/New York: Springer, 2009, pp. 3-32.
[Abstract] [BibTeX]This chapter outlines the state of the art of empirical and computational webgenre research. First, it highlights why the concept of genre is profitable for a range of disciplines. At the same time, it lists a number of recent interpretations that can inform and influence present and future genre research. Last but not least, it breaks down a series of open issues that relate to the modelling of the concept of webgenre in empirical and computational studies.
@InCollection{Santini:Mehler:Sharoff:2009, Author = {Santini, Marina and Mehler, Alexander and Sharoff, Serge}, Title = {Riding the Rough Waves of Genre on the Web: Concepts and Research Questions}, BookTitle = {Genres on the Web: Computational Models and Empirical Studies}, Publisher = {Springer}, Editor = {Mehler, Alexander and Sharoff, Serge and Santini, Marina}, Pages = {3-32}, Address = {Berlin/New York}, abstract = {This chapter outlines the state of the art of empirical and computational webgenre research. First, it highlights why the concept of genre is profitable for a range of disciplines. At the same time, it lists a number of recent interpretations that can inform and influence present and future genre research. Last but not least, it breaks down a series of open issues that relate to the modelling of the concept of webgenre in empirical and computational studies.}, crossref = {Genres on the Web: Computational Models and Empirical Studies}, year = 2009 }
-
A. Mehler, R. Gleim, U. Waltinger, A. Ernst, D. Esch, and T. Feith, "eHumanities Desktop – eine webbasierte Arbeitsumgebung für die geisteswissenschaftliche Fachinformatik," in Proceedings of the Symposium "Sprachtechnologie und eHumanities", 26.–27. Februar, Duisburg-Essen University, 2009.
[BibTeX]@InProceedings{Mehler:Gleim:Waltinger:Ernst:Esch:Feith:2009, Author = {Mehler, Alexander and Gleim, Rüdiger and Waltinger, Ulli and Ernst, Alexandra and Esch, Dietmar and Feith, Tobias}, Title = {eHumanities Desktop – eine webbasierte Arbeitsumgebung für die geisteswissenschaftliche Fachinformatik}, BookTitle = {Proceedings of the Symposium "Sprachtechnologie und eHumanities", 26.–27. Februar, Duisburg-Essen University}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_gleim_waltinger_ernst_esch_feith_2009.pdf}, website = {http://duepublico.uni-duisburg-essen.de/servlets/DocumentServlet?id=37041}, year = 2009 }
-
B. Wagner, A. Mehler, C. Wolff, and B. Dotzler, "Bausteine eines Literary Memory Information System (LiMeS) am Beispiel der Kafka-Forschung," in Proceedings of the Symposium "Sprachtechnologie und eHumanities", 26.–27. Februar, Duisburg-Essen University, 2009.
[Abstract] [BibTeX]In dem Paper beschreiben wir Bausteine eines Literary Memory Information System (LiMeS), das die literaturwissenschaftliche Erforschung von so genannten Matrixtexten – das sind Primärtexte eines bestimmten literarischen Gesamtwerks – unter dem Blickwinkel großer Mengen so genannter Echotexte (Topia 1984; Wagner/Reinhard 2007) – das sind Subtexte im Sinne eines literaturwissenschaftlichen Intertextualitätsbegriffs – ermöglicht. Den Ausgangspunkt dieses computerphilologischen Informationssystems bildet ein Text-Mining-Modell basierend auf dem Intertextualitätsbegriff in Verbindung mit dem Begriff des Semantic Web (Mehler, 2004b, 2005a, b, Wolff 2005). Wir zeigen, inwiefern dieses Modell über bestehende Informationssystemarchitekturen hinausgeht und schließen einen Brückenschlag zur derzeitigen Entwicklung von Arbeitsumgebungen in der geisteswissenschaftlichen Fachinformatik in Form eines eHumanities Desktop.
@InProceedings{Wagner:Mehler:Wolff:Dotzler:2009, Author = {Wagner, Benno and Mehler, Alexander and Wolff, Christian and Dotzler, Bernhard}, Title = {Bausteine eines Literary Memory Information System (LiMeS) am Beispiel der Kafka-Forschung}, BookTitle = {Proceedings of the Symposium "Sprachtechnologie und eHumanities", 26.–27. Februar, Duisburg-Essen University}, abstract = {In dem Paper beschreiben wir Bausteine eines Literary Memory Information System (LiMeS), das die literaturwissenschaftliche Erforschung von so genannten Matrixtexten – das sind Prim{\"a}rtexte eines bestimmten literarischen Gesamtwerks – unter dem Blickwinkel gro{\ss}er Mengen so genannter Echotexte (Topia 1984; Wagner/Reinhard 2007) – das sind Subtexte im Sinne eines literaturwissenschaftlichen Intertextualit{\"a}tsbegriffs – ermöglicht. Den Ausgangspunkt dieses computerphilologischen Informationssystems bildet ein Text-Mining-Modell basierend auf dem Intertextualit{\"a}tsbegriff in Verbindung mit dem Begriff des Semantic Web (Mehler, 2004b, 2005a, b, Wolff 2005). Wir zeigen, inwiefern dieses Modell über bestehende Informationssystemarchitekturen hinausgeht und schlie{\ss}en einen Brückenschlag zur derzeitigen Entwicklung von Arbeitsumgebungen in der geisteswissenschaftlichen Fachinformatik in Form eines eHumanities Desktop.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/wagner_mehler_wolff_dotzler_2009.pdf}, website = {http://epub.uni-regensburg.de/6795/}, year = 2009 }
-
U. Waltinger, A. Mehler, and A. Wegner, "A Two-Level Approach to Web Genre Classification," in Proceedings of the 5th International Conference on Web Information Systems and Technologies (WEBIST '09), March 23-26, 2009, Lisboa, 2009.
[Abstract] [BibTeX]This paper presents an approach of two-level categorization of web pages. In contrast to related approaches the model additionally explores and categorizes functionally and thematically demarcated segments of the hypertext types to be categorized. By classifying these segments conclusions can be drawn about the type of the corresponding compound web document.
@InProceedings{Waltinger:Mehler:Wegner:2009, Author = {Waltinger, Ulli and Mehler, Alexander and Wegner, Armin}, Title = {A Two-Level Approach to Web Genre Classification}, BookTitle = {Proceedings of the 5th International Conference on Web Information Systems and Technologies (WEBIST '09), March 23-26, 2009, Lisboa}, abstract = {This paper presents an approach of two-level categorization of web pages. In contrast to related approaches the model additionally explores and categorizes functionally and thematically demarcated segments of the hypertext types to be categorized. By classifying these segments conclusions can be drawn about the type of the corresponding compound web document.}, pdf = {http://www.ulliwaltinger.de/pdf/Webist_2009_TwoLevel_Genre_Classification_WaltingerMehlerWegner.pdf}, year = 2009 }
-
A. Mehler, "Structure Formation in the Web. A Graph-Theoretical Model of Hypertext Types," in Linguistic Modeling of Information and Markup Languages. Contributions to Language Technology, A. Witt and D. Metzing, Eds., Dordrecht: Springer, 2009.
[Abstract] [BibTeX]In this chapter we develop a representation model of web document networks. Based on the notion of uncertain web document structures, the model is defined as a template which grasps nested manifestation levels of hypertext types. Further, we specify the model on the conceptual, formal and physical level and exemplify it by reconstructing competing web document models.
@InCollection{Mehler:2009:b, Author = {Mehler, Alexander}, Title = {Structure Formation in the Web. A Graph-Theoretical Model of Hypertext Types}, BookTitle = {Linguistic Modeling of Information and Markup Languages. Contributions to Language Technology}, Publisher = {Springer}, Editor = {Witt, Andreas and Metzing, Dieter}, Series = {Text, Speech and Language Technology}, Address = {Dordrecht}, abstract = {In this chapter we develop a representation model of web document networks. Based on the notion of uncertain web document structures, the model is defined as a template which grasps nested manifestation levels of hypertext types. Further, we specify the model on the conceptual, formal and physical level and exemplify it by reconstructing competing web document models.}, website = {http://www.springerlink.com/content/t27782w8j2125112/}, year = 2009 }
-
R. Gleim, A. Mehler, U. Waltinger, and P. Menke, "eHumanities Desktop – An extensible Online System for Corpus Management and Analysis," in 5th Corpus Linguistics Conference, University of Liverpool, 2009.
[Abstract] [BibTeX]This paper presents the eHumanities Desktop - an online system for corpus management and analysis in support of computing in the humanities. Design issues and the overall architecture are described, as well as an outline of the applications offered by the system.
@InProceedings{Gleim:Mehler:Waltinger:Menke:2009, Author = {Gleim, Rüdiger and Mehler, Alexander and Waltinger, Ulli and Menke, Peter}, Title = {eHumanities Desktop – An extensible Online System for Corpus Management and Analysis}, BookTitle = {5th Corpus Linguistics Conference, University of Liverpool}, abstract = {This paper presents the eHumanities Desktop - an online system for corpus management and analysis in support of computing in the humanities. Design issues and the overall architecture are described, as well as an outline of the applications offered by the system.}, pdf = {http://www.ulliwaltinger.de/pdf/eHumanitiesDesktop-AnExtensibleOnlineSystem-CL2009.pdf}, website = {http://www.ulliwaltinger.de/ehumanities-desktop-an-extensible-online-system-for-corpus-management-and-analysis/}, year = 2009 }
-
A. Mehler and A. Lücking, "A Structural Model of Semiotic Alignment: The Classification of Multimodal Ensembles as a Novel Machine Learning Task," in Proceedings of IEEE Africon 2009, September 23-25, Nairobi, Kenya, 2009.
[Abstract] [BibTeX]In addition to the well-known linguistic alignment processes in dyadic communication – e.g., phonetic, syntactic, semantic alignment – we provide evidence for a genuine multimodal alignment process, namely semiotic alignment. Communicative elements from different modalities 'routinize into' cross-modal 'super-signs', which we call multimodal ensembles. Computational models of human communication are in need of expressive models of multimodal ensembles. In this paper, we exemplify semiotic alignment by means of empirical examples of the building of multimodal ensembles. We then propose a graph model of multimodal dialogue that is expressive enough to capture multimodal ensembles. In line with this model, we define a novel task in machine learning with the aim of training classifiers that can detect semiotic alignment in dialogue. This model is in support of approaches which need to gain insights into realistic human-machine communication.
@InProceedings{Mehler:Luecking:2009, Author = {Mehler, Alexander and Lücking, Andy}, Title = {A Structural Model of Semiotic Alignment: The Classification of Multimodal Ensembles as a Novel Machine Learning Task}, BookTitle = {Proceedings of IEEE Africon 2009, September 23-25, Nairobi, Kenya}, Publisher = {IEEE}, abstract = {In addition to the well-known linguistic alignment processes in dyadic communication – e.g., phonetic, syntactic, semantic alignment – we provide evidence for a genuine multimodal alignment process, namely semiotic alignment. Communicative elements from different modalities 'routinize into' cross-modal 'super-signs', which we call multimodal ensembles. Computational models of human communication are in need of expressive models of multimodal ensembles. In this paper, we exemplify semiotic alignment by means of empirical examples of the building of multimodal ensembles. We then propose a graph model of multimodal dialogue that is expressive enough to capture multimodal ensembles. In line with this model, we define a novel task in machine learning with the aim of training classifiers that can detect semiotic alignment in dialogue. This model is in support of approaches which need to gain insights into realistic human-machine communication.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_luecking_2009.pdf}, website = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?reload=true&arnumber=5308098}, year = 2009 }
-
A. Mehler, "Generalized Shortest Paths Trees: A Novel Graph Class Applied to Semiotic Networks," in Analysis of Complex Networks: From Biology to Linguistics, M. Dehmer and F. Emmert-Streib, Eds., Weinheim: Wiley-VCH, 2009, pp. 175-220.
[BibTeX]@InCollection{Mehler:2009:c, Author = {Mehler, Alexander}, Title = {Generalized Shortest Paths Trees: A Novel Graph Class Applied to Semiotic Networks}, BookTitle = {Analysis of Complex Networks: From Biology to Linguistics}, Publisher = {Wiley-VCH}, Editor = {Dehmer, Matthias and Emmert-Streib, Frank}, Pages = {175-220}, Address = {Weinheim}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2009_b.pdf}, website = {https://www.researchgate.net/publication/255666602_1_Generalised_Shortest_Paths_Trees_A_Novel_Graph_Class_Applied_to_Semiotic_Networks}, year = 2009 }
-
T. vor der Brück and S. Hartrumpf, "A Readability Checker Based on Deep Semantic Indicators," in Human Language Technology. Challenges of the Information Society, Z. Vetulani and H. Uszkoreit, Eds., Berlin, Germany: Springer, 2009, vol. 5603, pp. 232-244.
[Abstract] [BibTeX]One major reason that readability checkers are still far away from judging the understandability of texts consists in the fact that no semantic information is used. Syntactic, lexical, or morphological information can only give limited access for estimating the cognitive difficulties for a human being to comprehend a text. In this paper however, we present a readability checker which uses semantic information in addition. This information is represented as semantic networks and is derived by a deep syntactico-semantic analysis. We investigate in which situations a semantic readability indicator can lead to superior results in comparison with ordinary surface indicators like sentence length. Finally, we compute the weights of our semantic indicators in the readability function based on the user ratings collected in an online evaluation.
@InCollection{vor:der:Brueck:Hartrumpf:2009, Author = {vor der Brück, Tim and Hartrumpf, Sven}, Title = {A Readability Checker Based on Deep Semantic Indicators}, BookTitle = {Human Language Technology. Challenges of the Information Society}, Publisher = {Springer}, Editor = {Zygmunt Vetulani and Hans Uszkoreit}, Volume = {5603}, Series = {Lecture Notes in Computer Science (LNCS)}, Pages = {232--244}, Address = {Berlin, Germany}, abstract = {One major reason that readability checkers are still far away from judging the understandability of texts consists in the fact that no semantic information is used. Syntactic, lexical, or morphological information can only give limited access for estimating the cognitive difficulties for a human being to comprehend a text. In this paper however, we present a readability checker which uses semantic information in addition. This information is represented as semantic networks and is derived by a deep syntactico-semantic analysis. We investigate in which situations a semantic readability indicator can lead to superior results in comparison with ordinary surface indicators like sentence length. Finally, we compute the weights of our semantic indicators in the readability function based on the user ratings collected in an online evaluation.}, website = {http://rd.springer.com/chapter/10.1007/978-3-642-04235-5_20}, year = 2009 }
-
T. vor der Brück, "Hypernymy Extraction Based on Shallow and Deep Patterns," in From Form To Meaning: Processing Texts Automatically, Proceedings of the Biennial GSCL Conference 2009, Potsdam, Germany, 2009, pp. 41-52.
[Abstract] [BibTeX]There exist various approaches to construct taxonomies by text mining. Usually these approaches are based on supervised learning and extract in a first step several patterns. These patterns are then applied to previously unseen texts and used to recognize hypernym/hyponym pairs. Normally these approaches are only based on a surface representation or a syntactic tree structure, i.e., a constituency or dependency tree derived by a syntactical parser. In this work we present an approach which, additionally to shallow patterns, directly operates on semantic networks which are derived by a deep linguistic syntacticosemantic analysis. Furthermore, the shallow approach heavily depends on semantic information, too. It is shown that recall and precision can be improved considerably than by relying on shallow patterns alone.
@InProceedings{vor:der:Brueck:2009:b, Author = {vor der Brück, Tim}, Title = {Hypernymy Extraction Based on Shallow and Deep Patterns}, BookTitle = {From Form To Meaning: Processing Texts Automatically, Proceedings of the Biennial GSCL Conference 2009}, Editor = {Christian Chiarcos and Richard Eckart de Castilho}, Pages = {41--52}, Address = {Potsdam, Germany}, abstract = {There exist various approaches to construct taxonomies by text mining. Usually these approaches are based on supervised learning and extract in a first step several patterns. These patterns are then applied to previously unseen texts and used to recognize hypernym/hyponym pairs. Normally these approaches are only based on a surface representation or a syntactic tree structure, i.e., a constituency or dependency tree derived by a syntactical parser. In this work we present an approach which, additionally to shallow patterns, directly operates on semantic networks which are derived by a deep linguistic syntacticosemantic analysis. Furthermore, the shallow approach heavily depends on semantic information, too. It is shown that recall and precision can be improved considerably than by relying on shallow patterns alone.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gscl09_12_brueck.pdf}, year = 2009 }
-
G. Bouma, S. Duarte, and M. Z. Islam, "Cross-lingual Alignment and Completion of Wikipedia Templates," in Third International Workshop on Cross Lingual Information Access: Addressing the Information Need of Multilingual Societies (CLIAWS3), Boulder, Colorado, USA, June 4, 2009.
[Abstract] [BibTeX]For many languages, the size of Wikipedia is an order of magnitude smaller than the English Wikipedia. We present a method for cross-lingual alignment of template and infobox attributes in Wikipedia. The alignment is used to add and complete templates and infoboxes in one language with information derived from Wikipedia in another language. We show that alignment between English and Dutch Wikipedia is accurate and that the result can be used to expand the number of template attribute-value pairs in Dutch Wikipedia by 50%. Furthermore, the alignment provides valuable information for normalization of template and attribute names and can be used to detect potential inconsistencies
@InProceedings{Bouma:Duarte:Zahurul:2009, Author = {Bouma, Gosse and Duarte, Sergio and Islam, Md. Zahurul}, Title = {Cross-lingual Alignment and Completion of Wikipedia Templates}, BookTitle = {Third International Workshop on Cross Lingual Information Access: Addressing the Information Need of Multilingual Societies (CLIAWS3), Boulder, Colorado, USA, June 4}, abstract = {For many languages, the size of Wikipedia is an order of magnitude smaller than the English Wikipedia. We present a method for cross-lingual alignment of template and infobox attributes in Wikipedia. The alignment is used to add and complete templates and infoboxes in one language with information derived from Wikipedia in another language. We show that alignment between English and Dutch Wikipedia is accurate and that the result can be used to expand the number of template attribute-value pairs in Dutch Wikipedia by 50%. Furthermore, the alignment provides valuable information for normalization of template and attribute names and can be used to detect potential inconsistencies}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Cross-lingual_Alignment_and_Completion_of_Wikipedia_Templates.pdf}, timestamp = {2011.08.02}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.1418}, year = 2009 }
-
U. Waltinger, "Polarity Reinforcement: Sentiment Polarity Identification By Means Of Social Semantics," in Proceedings of the IEEE Africon 2009, September 23-25, Nairobi, Kenya, 2009.
[BibTeX]@InProceedings{Waltinger:2009:a, Author = {Waltinger, Ulli}, Title = {Polarity Reinforcement: Sentiment Polarity Identification By Means Of Social Semantics}, BookTitle = {Proceedings of the IEEE Africon 2009, September 23-25, Nairobi, Kenya}, date_0 = {2009}, pdf = {http://www.ulliwaltinger.de/pdf/AfriconIEEE_2009_SentimentPolarity_Waltinger.pdf}, website = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5308104}, year = 2009 }
-
U. Waltinger, I. Cramer, and T. Wandmacher, "From Social Networks To Distributional Properties: A Comparative Study On Computing Semantic Relatedness," in Proceedings of the 31th Annual Conference of the Cognitive Science Society, Austin, TX, 2009, pp. 3016-3021.
[BibTeX]@InProceedings{Waltinger:Cramer:Wandmacher:2009:a, Author = {Waltinger, Ulli and Cramer, Irene and Wandmacher, Tonio}, Title = {From Social Networks To Distributional Properties: A Comparative Study On Computing Semantic Relatedness}, BookTitle = {Proceedings of the 31th Annual Conference of the Cognitive Science Society}, Editor = {Taatgen, N.A. and van Rijn, H.}, Pages = {3016-3021}, Address = {Austin, TX}, Publisher = {Cognitive Science Society}, date_0 = {2009}, pdf = {http://csjarchive.cogsci.rpi.edu/proceedings/2009/papers/661/paper661.pdf}, year = 2009 }
-
U. Waltinger, "Polarity Reinforcement: Sentiment Polarity Identification By Means Of Social Semantics," in Proceedings of the IEEE Africon 2009, September 23-25, Nairobi, Kenya, 2009.
[BibTeX]@InProceedings{Waltinger:2009:b, Author = {Waltinger, Ulli}, Title = {Polarity Reinforcement: Sentiment Polarity Identification By Means Of Social Semantics}, BookTitle = {Proceedings of the IEEE Africon 2009, September 23-25, Nairobi, Kenya}, date_0 = {2009}, year = 2009 }
-
U. Waltinger, I. Cramer, and T. Wandmacher, "From Social Networks To Distributional Properties: A Comparative Study On Computing Semantic Relatedness," in Proceedings of the 31th Annual Conference of the Cognitive Science Society, Austin, TX, 2009, pp. 3016-3021.
[BibTeX]@InProceedings{Waltinger:Cramer:Wandmacher:2009:b, Author = {Waltinger, Ulli and Cramer, Irene and Wandmacher, Tonio}, Title = {From Social Networks To Distributional Properties: A Comparative Study On Computing Semantic Relatedness}, BookTitle = {Proceedings of the 31th Annual Conference of the Cognitive Science Society}, Editor = {N.A. Taatgen and H. van Rijn}, Pages = {3016-3021}, Address = {Austin, TX}, Publisher = {Cognitive Science Society}, date_0 = {2009}, year = 2009 }
-
A. Mehler and U. Waltinger, "Enhancing Document Modeling by Means of Open Topic Models: Crossing the Frontier of Classification Schemes in Digital Libraries by Example of the DDC," Library Hi Tech, vol. 27, iss. 4, pp. 520-539, 2009.
[Abstract] [BibTeX]Purpose: We present a topic classification model using the Dewey Decimal Classification (DDC) as the target scheme. This is done by exploring metadata as provided by the Open Archives Initiative (OAI) to derive document snippets as minimal document representations. The reason is to reduce the effort of document processing in digital libraries. Further, we perform feature selection and extension by means of social ontologies and related web-based lexical resources. This is done to provide reliable topic-related classifications while circumventing the problem of data sparseness. Finally, we evaluate our model by means of two language-specific corpora. This paper bridges digital libraries on the one hand and computational linguistics on the other. The aim is to make accessible computational linguistic methods to provide thematic classifications in digital libraries based on closed topic models as the DDC. Design/methodology/approach: text classification, text-technology, computational linguistics, computational semantics, social semantics. Findings: We show that SVM-based classifiers perform best by exploring certain selections of OAI document metadata. Research limitations/implications: The findings show that it is necessary to further develop SVM-based DDC-classifiers by using larger training sets possibly for more than two languages in order to get better F-measure values. Practical implications: We can show that DDC-classifications come into reach which primarily explore OAI metadata. Originality/value: We provide algorithmic and formal-mathematical information how to build DDC-classifiers for digital libraries.
@Article{Mehler:Waltinger:2009:b, Author = {Mehler, Alexander and Waltinger, Ulli}, Title = {Enhancing Document Modeling by Means of Open Topic Models: Crossing the Frontier of Classification Schemes in Digital Libraries by Example of the DDC}, Journal = {Library Hi Tech}, Volume = {27}, Number = {4}, Pages = {520-539}, abstract = {Purpose: We present a topic classification model using the Dewey Decimal Classification (DDC) as the target scheme. This is done by exploring metadata as provided by the Open Archives Initiative (OAI) to derive document snippets as minimal document representations. The reason is to reduce the effort of document processing in digital libraries. Further, we perform feature selection and extension by means of social ontologies and related web-based lexical resources. This is done to provide reliable topic-related classifications while circumventing the problem of data sparseness. Finally, we evaluate our model by means of two language-specific corpora. This paper bridges digital libraries on the one hand and computational linguistics on the other. The aim is to make accessible computational linguistic methods to provide thematic classifications in digital libraries based on closed topic models as the DDC. Design/methodology/approach: text classification, text-technology, computational linguistics, computational semantics, social semantics. Findings: We show that SVM-based classifiers perform best by exploring certain selections of OAI document metadata. Research limitations/implications: The findings show that it is necessary to further develop SVM-based DDC-classifiers by using larger training sets possibly for more than two languages in order to get better F-measure values. Practical implications: We can show that DDC-classifications come into reach which primarily explore OAI metadata. Originality/value: We provide algorithmic and formal-mathematical information how to build DDC-classifiers for digital libraries.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_waltinger_2009_b.pdf}, website = {http://biecoll.ub.uni-bielefeld.de/frontdoor.php?source_opus=5001&la=de}, year = 2009 }
-
R. Gleim, U. Waltinger, A. Ernst, A. Mehler, D. Esch, and T. Feith, "The eHumanities Desktop – An Online System for Corpus Management and Analysis in Support of Computing in the Humanities," in Proceedings of the Demonstrations Session of the 12th Conference of the European Chapter of the Association for Computational Linguistics EACL 2009, 30 March – 3 April, Athens, 2009.
[BibTeX]@InProceedings{Gleim:Waltinger:Ernst:Mehler:Esch:Feith:2009, Author = {Gleim, Rüdiger and Waltinger, Ulli and Ernst, Alexandra and Mehler, Alexander and Esch, Dietmar and Feith, Tobias}, Title = {The eHumanities Desktop – An Online System for Corpus Management and Analysis in Support of Computing in the Humanities}, BookTitle = {Proceedings of the Demonstrations Session of the 12th Conference of the European Chapter of the Association for Computational Linguistics EACL 2009, 30 March – 3 April, Athens}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gleim_waltinger_ernst_mehler_esch_feith_2009.pdf}, year = 2009 }
-
A. Mehler, "Artifizielle Interaktivität. Eine semiotische Betrachtung," in Medienwandel als Wandel von Interaktionsformen – von frühen Medienkulturen zum Web 2.0, T. Sutter and A. Mehler, Eds., Wiesbaden: VS, 2009.
[BibTeX]@InCollection{Mehler:2009:d, Author = {Mehler, Alexander}, Title = {Artifizielle Interaktivit{\"a}t. Eine semiotische Betrachtung}, BookTitle = {Medienwandel als Wandel von Interaktionsformen – von frühen Medienkulturen zum Web 2.0}, Publisher = {VS}, Editor = {Sutter, Tilmann and Mehler, Alexander}, Address = {Wiesbaden}, year = 2009 }
-
U. Waltinger and A. Mehler, "The Feature Difference Coefficient: Classification by Means of Feature Distributions," in Proceedings of the Conference on Text Mining Services (TMS 2009), Leipzig, 2009, p. 159–168.
[BibTeX]@InProceedings{Waltinger:Mehler:2009:a, Author = {Waltinger, Ulli and Mehler, Alexander}, Title = {The Feature Difference Coefficient: Classification by Means of Feature Distributions}, BookTitle = {Proceedings of the Conference on Text Mining Services (TMS 2009)}, Series = {Leipziger Beitr{\"a}ge zur Informatik: Band XIV}, Pages = {159–168}, Address = {Leipzig}, Publisher = {Leipzig University}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/waltinger_mehler_2009_a.pdf}, year = 2009 }
-
M. Santini, G. Rehm, S. Sharoff, and A. Mehler, Automatic Genre Identification: Issues and Prospects, M. Santini, G. Rehm, S. Sharoff, and A. Mehler, Eds., GSCL, 2009, vol. 24(1).
[BibTeX]@Book{Santini:Rehm:Sharoff:Mehler:2009, Author = {Santini, Marina and Rehm, Georg and Sharoff, Serge and Mehler, Alexander}, Editor = {Santini, Marina and Rehm, Georg and Sharoff, Serge and Mehler, Alexander}, Title = {Automatic Genre Identification: Issues and Prospects}, Publisher = {GSCL}, Volume = {24(1)}, Series = {Journal for Language Technology and Computational Linguistics (JLCL)}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/AutomaticGenreIdentification.png}, pagetotal = {148}, pdf = {http://www.jlcl.org/2009_Heft1/JLCL24(1).pdf}, year = 2009 }
-
U. Waltinger, A. Mehler, and R. Gleim, "Social Semantics And Its Evaluation By Means of Closed Topic Models: An SVM-Classification Approach Using Semantic Feature Replacement By Topic Generalization," in Proceedings of the Biennial GSCL Conference 2009, September 30 – October 2, Universität Potsdam, 2009.
[BibTeX]@InProceedings{Waltinger:Mehler:Gleim:2009:a, Author = {Waltinger, Ulli and Mehler, Alexander and Gleim, Rüdiger}, Title = {Social Semantics And Its Evaluation By Means of Closed Topic Models: An SVM-Classification Approach Using Semantic Feature Replacement By Topic Generalization}, BookTitle = {Proceedings of the Biennial GSCL Conference 2009, September 30 – October 2, Universit{\"a}t Potsdam}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/GSCL_2009_WaltingerMehlerGleim_camera_ready.pdf}, year = 2009 }
-
U. Waltinger and A. Mehler, "Social Semantics and Its Evaluation By Means Of Semantic Relatedness And Open Topic Models," in IEEE/WIC/ACM International Conference on Web Intelligence, September 15–18, Milano, 2009.
[Abstract] [BibTeX]This paper presents an approach using social semantics for the task of topic labelling by means of Open Topic Models. Our approach utilizes a social ontology to create an alignment of documents within a social network. Comprised category information is used to compute a topic generalization. We propose a feature-frequency-based method for measuring semantic relatedness which is needed in order to reduce the number of document features for the task of topic labelling. This method is evaluated against multiple human judgement experiments comprising two languages and three different resources. Overall the results show that social ontologies provide a rich source of terminological knowledge. The performance of the semantic relatedness measure with correlation values of up to .77 are quite promising. Results on the topic labelling experiment show, with an accuracy of up to .79, that our approach can be a valuable method for various NLP applications.
@InProceedings{Waltinger:Mehler:2009:c, Author = {Waltinger, Ulli and Mehler, Alexander}, Title = {Social Semantics and Its Evaluation By Means Of Semantic Relatedness And Open Topic Models}, BookTitle = {IEEE/WIC/ACM International Conference on Web Intelligence, September 15–18, Milano}, abstract = {This paper presents an approach using social semantics for the task of topic labelling by means of Open Topic Models. Our approach utilizes a social ontology to create an alignment of documents within a social network. Comprised category information is used to compute a topic generalization. We propose a feature-frequency-based method for measuring semantic relatedness which is needed in order to reduce the number of document features for the task of topic labelling. This method is evaluated against multiple human judgement experiments comprising two languages and three different resources. Overall the results show that social ontologies provide a rich source of terminological knowledge. The performance of the semantic relatedness measure with correlation values of up to .77 are quite promising. Results on the topic labelling experiment show, with an accuracy of up to .79, that our approach can be a valuable method for various NLP applications.}, website = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5284920&abstractAccess=no&userType=inst}, year = 2009 }
-
T. vor der Brück, "Approximation of the Parameters of a Readability Formula by Robust Regression," in Machine Learning and Data Mining in Pattern recognition: Poster Proceedings of the International Conference on Machine Learning and Data Mining (MLDM), Leipzig, Germany, 2009, pp. 115-125.
[Abstract] [BibTeX]Most readability formulas calculate a global readability score by combining several indicator values by a linear combination. Typical indicators are Average sentence length, Average number of syllables per word, etc. Usually the parameters of the linear combination are determined by a linear OLS (ordinary least square estimation) minimizing the sum of the squared residuals in comparison with human ratings for a given set of texts. The usage of OLS leads to several drawbacks. First, the parameters are not constraint in any way and are therefore not intuitive and difficult to interpret. Second, if the number of parameters become large, the effect of overfitting easily occurs. Finally, OLS is quite sensitive to outliers. Therefore, an alternative method is presented which avoids these drawbacks and is based on robust regression.
@InProceedings{vor:der:Brueck:2009, Author = {vor der Brück, Tim}, Title = {Approximation of the Parameters of a Readability Formula by Robust Regression}, BookTitle = {Machine Learning and Data Mining in Pattern recognition: Poster Proceedings of the International Conference on Machine Learning and Data Mining (MLDM)}, Pages = {115--125}, Address = {Leipzig, Germany}, abstract = {Most readability formulas calculate a global readability score by combining several indicator values by a linear combination. Typical indicators are Average sentence length, Average number of syllables per word, etc. Usually the parameters of the linear combination are determined by a linear OLS (ordinary least square estimation) minimizing the sum of the squared residuals in comparison with human ratings for a given set of texts. The usage of OLS leads to several drawbacks. First, the parameters are not constraint in any way and are therefore not intuitive and difficult to interpret. Second, if the number of parameters become large, the effect of overfitting easily occurs. Finally, OLS is quite sensitive to outliers. Therefore, an alternative method is presented which avoids these drawbacks and is based on robust regression.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mldm_2009_brueck_142.pdf}, year = 2009 }
2008 (21)
-
M. Stührenberg, M. Beißwenger, K. Kühnberger, A. Mehler, H. Lüngen, D. Metzing, and U. Mönnich, "Sustainability of Text-Technological Resources," in Proceedings of the Post LREC-2008 Workshop: Sustainability of Language Resources and Tools for Natural Language Processing Marrakech, Morocco, 2008.
[Abstract] [BibTeX]We consider that there are obvious relationships between research on sustainability of language and linguistic resources on the one hand and work undertaken in the Research Unit 'Text-Technological Modelling of Information' on the other. Currently the main focus in sustainability research is concerned with archiving methods of textual resources, i.e. methods for sustainability of primary and secondary data; these aspects are addressed in our work as well. However, we believe that there are additional certain aspects of sustainability on which new light is shed on by procedures, algorithms and dynamic processes undertaken in our Research Unit
@InProceedings{Stuehrenberg:Beisswenger:Kuehnberger:Mehler:Luengen:Metzing:Moennich:2008, Author = {Stührenberg, Maik and Bei{\ss}wenger, Michael and Kühnberger, Kai-Uwe and Mehler, Alexander and Lüngen, Harald and Metzing, Dieter and Mönnich, Uwe}, Title = {Sustainability of Text-Technological Resources}, BookTitle = {Proceedings of the Post LREC-2008 Workshop: Sustainability of Language Resources and Tools for Natural Language Processing Marrakech, Morocco}, abstract = {We consider that there are obvious relationships between research on sustainability of language and linguistic resources on the one hand and work undertaken in the Research Unit 'Text-Technological Modelling of Information' on the other. Currently the main focus in sustainability research is concerned with archiving methods of textual resources, i.e. methods for sustainability of primary and secondary data; these aspects are addressed in our work as well. However, we believe that there are additional certain aspects of sustainability on which new light is shed on by procedures, algorithms and dynamic processes undertaken in our Research Unit}, pdf = {http://www.michael-beisswenger.de/pub/lrec-sustainability.pdf}, year = 2008 }
-
A. Mehler, B. Job, P. Blanchard, and H. Eikmeyer, "Sprachliche Netzwerke," in Netzwerkanalyse und Netzwerktheorie, C. Stegbauer, Ed., Wiesbaden: VS, 2008, pp. 413-427.
[Abstract] [BibTeX]In diesem Kapitel beschreiben wir so genannte sprachliche Netzwerke. Dabei handelt es sich um Netzwerke sprachlicher Einheiten, die in Zusammenhang mit ihrer Einbettung in das Netzwerk jener Sprachgemeinschaft analysiert werden, welche diese Einheiten und deren Vernetzung hervorgebracht hat. Wir erörtern ein Dreistufenmodell zur Analyse solcher Netzwerke und exemplifizieren dieses Modell anhand mehrerer Spezialwikis. Ein Hauptaugenmerk des Kapitels liegt dabei auf einem Mehrebenennetzwerkmodell, und zwar in Abkehr von den unipartiten Graphmodellen der Theorie komplexer Netzwerke.
@InCollection{Mehler:Job:Blanchard:Eikmeyer:2008, Author = {Mehler, Alexander and Job, Barbara and Blanchard, Philippe and Eikmeyer, Hans-Jürgen}, Title = {Sprachliche Netzwerke}, BookTitle = {Netzwerkanalyse und Netzwerktheorie}, Publisher = {VS}, Editor = {Stegbauer, Christian}, Pages = {413-427}, Address = {Wiesbaden}, abstract = {In diesem Kapitel beschreiben wir so genannte sprachliche Netzwerke. Dabei handelt es sich um Netzwerke sprachlicher Einheiten, die in Zusammenhang mit ihrer Einbettung in das Netzwerk jener Sprachgemeinschaft analysiert werden, welche diese Einheiten und deren Vernetzung hervorgebracht hat. Wir erörtern ein Dreistufenmodell zur Analyse solcher Netzwerke und exemplifizieren dieses Modell anhand mehrerer Spezialwikis. Ein Hauptaugenmerk des Kapitels liegt dabei auf einem Mehrebenennetzwerkmodell, und zwar in Abkehr von den unipartiten Graphmodellen der Theorie komplexer Netzwerke.}, year = 2008 }
-
O. Abramov, A. Mehler, and R. Gleim, "A Unified Database of Dependency Treebanks. Integrating, Quantifying and Evaluating Dependency Data," in Proceedings of the 6th Language Resources and Evaluation Conference (LREC 2008), Marrakech (Morocco), 2008.
[Abstract] [BibTeX]This paper describes a database of 11 dependency treebanks which were unified by means of a two-dimensional graph format. The format was evaluated with respect to storage-complexity on the one hand, and efficiency of data access on the other hand. An example of how the treebanks can be integrated within a unique interface is given by means of the DTDB interface.
@InProceedings{Pustylnikov:Mehler:Gleim:2008, Author = {Abramov, Olga and Mehler, Alexander and Gleim, Rüdiger}, Title = {A Unified Database of Dependency Treebanks. Integrating, Quantifying and Evaluating Dependency Data}, BookTitle = {Proceedings of the 6th Language Resources and Evaluation Conference (LREC 2008), Marrakech (Morocco)}, abstract = {This paper describes a database of 11 dependency treebanks which were unified by means of a two-dimensional graph format. The format was evaluated with respect to storage-complexity on the one hand, and efficiency of data access on the other hand. An example of how the treebanks can be integrated within a unique interface is given by means of the DTDB interface. }, pdf = {http://wwwhomes.uni-bielefeld.de/opustylnikov/pustylnikov/pdfs/LREC08_full.pdf}, year = 2008 }
-
A. Mehler, "Structural Similarities of Complex Networks: A Computational Model by Example of Wiki Graphs," Applied Artificial Intelligence, vol. 22, iss. 7&8, p. 619–683, 2008.
[Abstract] [BibTeX]This article elaborates a framework for representing and classifying large complex networks by example of wiki graphs. By means of this framework we reliably measure the similarity of document, agent, and word networks by solely regarding their topology. In doing so, the article departs from classical approaches to complex network theory which focuses on topological characteristics in order to check their small world property. This does not only include characteristics that have been studied in complex network theory, but also some of those which were invented in social network analysis and hypertext theory. We show that network classifications come into reach which go beyond the hypertext structures traditionally analyzed in web mining. The reason is that we focus on networks as a whole as units to be classified—above the level of websites and their constitutive pages. As a consequence, we bridge classical approaches to text and web mining on the one hand and complex network theory on the other hand. Last but not least, this approach also provides a framework for quantifying the linguistic notion of intertextuality.
@Article{Mehler:2008:a, Author = {Mehler, Alexander}, Title = {Structural Similarities of Complex Networks: A Computational Model by Example of Wiki Graphs}, Journal = {Applied Artificial Intelligence}, Volume = {22}, Number = {7\&8}, Pages = {619–683}, abstract = {This article elaborates a framework for representing and classifying large complex networks by example of wiki graphs. By means of this framework we reliably measure the similarity of document, agent, and word networks by solely regarding their topology. In doing so, the article departs from classical approaches to complex network theory which focuses on topological characteristics in order to check their small world property. This does not only include characteristics that have been studied in complex network theory, but also some of those which were invented in social network analysis and hypertext theory. We show that network classifications come into reach which go beyond the hypertext structures traditionally analyzed in web mining. The reason is that we focus on networks as a whole as units to be classified—above the level of websites and their constitutive pages. As a consequence, we bridge classical approaches to text and web mining on the one hand and complex network theory on the other hand. Last but not least, this approach also provides a framework for quantifying the linguistic notion of intertextuality.}, doi = {10.1080/08839510802164085}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2016/10/mehler_2008_Structural_Similarities_of_Complex_Networks.pdf}, website = {https://www.researchgate.net/publication/200772675_Structural_similarities_of_complex_networks_A_computational_model_by_example_of_wiki_graphs}, year = 2008 }
-
A. Mehler, Lexical-Semantic Resources in Automated Discourse Analysis, H. Lüngen, A. Mehler, and A. Storrer, Eds., GSCL, 2008, vol. 23(2).
[BibTeX]@Book{Luengen:Mehler:Storrer:2008:a, Author = {Mehler, Alexander}, Editor = {Lüngen, Harald and Mehler, Alexander and Storrer, Angelika}, Title = {Lexical-Semantic Resources in Automated Discourse Analysis}, Publisher = {GSCL}, Volume = {23(2)}, Series = {Journal for Language Technology and Computational Linguistics (JLCL)}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/LexicalSemanticResources-300-20.png}, pagetotal = {111}, pdf = {{http://www.jlcl.org/2008_Heft2/JLCL23(2).pdf}}, website = {https://www.researchgate.net/publication/228956889_Lexical-Semantic_Resources_in_Automated_Discourse_Analysis}, year = 2008 }
-
A. Mehler, "Large Text Networks as an Object of Corpus Linguistic Studies," in Corpus Linguistics. An International Handbook of the Science of Language and Society, A. Lüdeling and M. Kytö, Eds., Berlin/New York: De Gruyter, 2008, p. 328–382.
[BibTeX]@InCollection{Mehler:2008:b, Author = {Mehler, Alexander}, Title = {Large Text Networks as an Object of Corpus Linguistic Studies}, BookTitle = {Corpus Linguistics. An International Handbook of the Science of Language and Society}, Publisher = {De Gruyter}, Editor = {Lüdeling, Anke and Kytö, Merja}, Pages = {328–382}, Address = {Berlin/New York}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2007_a.pdf}, year = 2008 }
-
T. vor der Brück and H. Stenzhorn, "A Dynamic Approach for Automatic Error Detection in Generation Grammars," in Proceedings of the 18th European Conference on Artificial Intelligence (ECAI), Patras, Greece, 2008.
[Abstract] [BibTeX]In any real world application scenario, natural language generation (NLG) systems have to employ grammars consisting of tremendous amounts of rules. Detecting and fixing errors in such grammars is therefore a highly tedious task. In this work we present a data mining algorithm which deduces incorrect grammar rules by abductive reasoning out of positive and negative training examples. More specifcally, the constituency trees belonging to successful generation processes and the incomplete trees of failed ones are analyzed. From this a quality score is derived for each grammar rule by analyzing the occurrences of the rules in the trees and by spotting the exact error locations in the incomplete trees. In prior work on automatic error detection v.d.Brück et al. [5] proposed a static error detection algorithm for generation grammars. The approach of Cussens et al. creates missing grammar rules for parsing using abduction [1]. Zeller introduced a dynamic approach in the related area of detecting errors in computer programs [6].
@InProceedings{vor:der:Brueck:Stenzhorn:2008, Author = {vor der Brück, Tim and Stenzhorn, Holger}, Title = {A Dynamic Approach for Automatic Error Detection in Generation Grammars}, BookTitle = {Proceedings of the 18th European Conference on Artificial Intelligence (ECAI)}, Address = {Patras, Greece}, abstract = {In any real world application scenario, natural language generation (NLG) systems have to employ grammars consisting of tremendous amounts of rules. Detecting and fixing errors in such grammars is therefore a highly tedious task. In this work we present a data mining algorithm which deduces incorrect grammar rules by abductive reasoning out of positive and negative training examples. More specifcally, the constituency trees belonging to successful generation processes and the incomplete trees of failed ones are analyzed. From this a quality score is derived for each grammar rule by analyzing the occurrences of the rules in the trees and by spotting the exact error locations in the incomplete trees. In prior work on automatic error detection v.d.Brück et al. [5] proposed a static error detection algorithm for generation grammars. The approach of Cussens et al. creates missing grammar rules for parsing using abduction [1]. Zeller introduced a dynamic approach in the related area of detecting errors in computer programs [6].}, isbn = {978-1-58603-891-5}, month = {July}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/xtragen_egram.pdf}, year = 2008 }
-
T. vor der Brück, S. Hartrumpf, and H. Helbig, "A Readability Checker with Supervised Learning using Deep Syntactic and Semantic Indicators," in Proceedings of the 11th International Multiconference: Information Society - IS 2008 - Language Technologies, Ljubljana, Slovenia, 2008, pp. 92-97.
[Abstract] [BibTeX]Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surfaceoriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score. Povzetek: Strojno učenje z odvisnostnimi drevesi je uporabljeno za ugotavljanje berljivosti besedil. 1
@InProceedings{vor:der:Brueck:Hartrumpf:Helbig:2008:a, Author = {vor der Brück, Tim and Hartrumpf, Sven and Helbig, Hermann}, Title = {A Readability Checker with Supervised Learning using Deep Syntactic and Semantic Indicators}, BookTitle = {Proceedings of the 11th International Multiconference: Information Society - IS 2008 - Language Technologies}, Editor = {Erjavec, Tomaž and Gros, Jerneja Žganec}, Pages = {92--97}, Address = {Ljubljana, Slovenia}, abstract = {Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surfaceoriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score. Povzetek: Strojno učenje z odvisnostnimi drevesi je uporabljeno za ugotavljanje berljivosti besedil. 1}, isbn = {987-961-264-006-4}, month = {October}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/brueck_hartrumpf_helbig08.pdf}, url = {http://pi7.fernuni-hagen.de/brueck/papers/brueck_hartrumpf_helbig08.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.5878}, year = 2008 }
-
T. vor der Brück, S. Hartrumpf, and H. Helbig, "A Readability Checker with Supervised Learning using Deep Indicators," Informatica, vol. 32, iss. 4, pp. 429-435, 2008.
[Abstract] [BibTeX]Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surface-oriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score.
@Article{vor:der:Brueck:Hartrumpf:Helbig:2008:b, Author = {vor der Brück, Tim and Hartrumpf, Sven and Helbig, Hermann}, Title = {A Readability Checker with Supervised Learning using Deep Indicators}, Journal = {Informatica}, Volume = {32}, Number = {4}, Pages = {429--435}, abstract = {Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surface-oriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed that the deep syntactic and semantic indicators lead to promising results comparable to the best surface-based indicators. The combination of deep and shallow indicators leads to an improvement over shallow indicators alone. Finally, a graphical user interface was developed which highlights difficult passages, depending on the individual indicator values, and displays a global readability score.}, website = {http://connection.ebscohost.com/c/articles/36288796/readability-checker-supervised-learning-using-deep-indicators}, year = 2008 }
-
O. Pustylnikov and A. Mehler, "Text classification by means of structural features. What kind of information about texts is captured by their structure?," in Proceedings of RUSSIR '08, September 1-5, Taganrog, Russia, 2008.
[BibTeX]@InProceedings{Pustylnikov:Mehler:2008:c, Author = {Pustylnikov, Olga and Mehler, Alexander}, Title = {Text classification by means of structural features. What kind of information about texts is captured by their structure?}, BookTitle = {Proceedings of RUSSIR '08, September 1-5, Taganrog, Russia}, pdf = {http://www.www.texttechnologylab.org/data/pdf/mehler_geibel_pustylnikov_2007.pdf}, year = 2008 }
-
U. Waltinger, A. Mehler, and M. Stührenberg, "An Integrated Model of Lexical Chaining: Applications, Resources and their Format," in Proceedings of KONVENS 2008 – Ergänzungsband Textressourcen und lexikalisches Wissen, 2008, pp. 59-70.
[BibTeX]@InProceedings{Waltinger:Mehler:Stuehrenberg:2008, Author = {Waltinger, Ulli and Mehler, Alexander and Stührenberg, Maik}, Title = {An Integrated Model of Lexical Chaining: Applications, Resources and their Format}, BookTitle = {Proceedings of KONVENS 2008 – Erg{\"a}nzungsband Textressourcen und lexikalisches Wissen}, Editor = {Storrer, Angelika and Geyken, Alexander and Siebert, Alexander and Würzner, Kay-Michael}, Pages = {59-70}, pdf = {http://www.ulliwaltinger.de/pdf/Konvens_2008_Integrated_Model_of_Lexical_Chaining_WaltingerMehlerStuehrenberg.pdf}, year = 2008 }
-
A. Mehler, "A Model of the Distribution of the Distances of Alike Elements in Dialogical Communication," in Proceedings of the International Conference on Information Theory and Statistical Learning (ITSL '08), July 14-15, 2008, Las Vegas, 2008, pp. 45-50.
[BibTeX]@InProceedings{Mehler:2008:c, Author = {Mehler, Alexander}, Title = {A Model of the Distribution of the Distances of Alike Elements in Dialogical Communication}, BookTitle = {Proceedings of the International Conference on Information Theory and Statistical Learning (ITSL '08), July 14-15, 2008, Las Vegas}, Pages = {45-50}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2008_c.pdf}, year = 2008 }
-
U. Waltinger, A. Mehler, and G. Heyer, "Towards Automatic Content Tagging: Enhanced Web Services in Digital Libraries Using Lexical Chaining," in 4th Int. Conf. on Web Information Systems and Technologies (WEBIST '08), 4-7 May, Funchal, Portugal, Barcelona, 2008, pp. 231-236.
[BibTeX]@InProceedings{Waltinger:Mehler:Heyer:2008, Author = {Waltinger, Ulli and Mehler, Alexander and Heyer, Gerhard}, Title = {Towards Automatic Content Tagging: Enhanced Web Services in Digital Libraries Using Lexical Chaining}, BookTitle = {4th Int. Conf. on Web Information Systems and Technologies (WEBIST '08), 4-7 May, Funchal, Portugal}, Editor = {Cordeiro, José and Filipe, Joaquim and Hammoudi, Slimane}, Pages = {231-236}, Address = {Barcelona}, Publisher = {INSTICC Press}, pdf = {http://www.ulliwaltinger.de/pdf/Webist_2008_Towards_Automatic_Content_Tagging_WaltingerMehlerHeyer.pdf}, url = {http://dblp.uni-trier.de/db/conf/webist/webist2008-2.html#WaltingerMH08}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.463.3097}, year = 2008 }
-
A. Mehler, "A Short Note on Social-Semiotic Networks from the Point of View of Quantitative Semantics," in Proceedings of the Dagstuhl Seminar on Social Web Communities, September 21-26, Dagstuhl, 2008.
[BibTeX]@InProceedings{Mehler:2008:f, Author = {Mehler, Alexander}, Title = {A Short Note on Social-Semiotic Networks from the Point of View of Quantitative Semantics}, BookTitle = {Proceedings of the Dagstuhl Seminar on Social Web Communities, September 21-26, Dagstuhl}, Editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd}, pdf = {http://drops.dagstuhl.de/opus/volltexte/2008/1788/pdf/08391.MehlerAlexander.ExtAbstract.1788.pdf}, year = 2008 }
-
A. Mehler, R. Gleim, A. Ernst, and U. Waltinger, "WikiDB: Building Interoperable Wiki-Based Knowledge Resources for Semantic Databases," Sprache und Datenverarbeitung. International Journal for Language Data Processing, vol. 32, iss. 1, pp. 47-70, 2008.
[Abstract] [BibTeX]This article describes an API for exploring the logical document and the logical network structure of wikis. It introduces an algorithm for the semantic preprocessing, filtering and typing of these building blocks. Further, this article models the process of wiki generation based on a unified format of syntactic, semantic and pragmatic representations. This three-level approach to make accessible syntactic, semantic and pragmatic aspects of wiki-based structure formation is complemented by a corresponding database model – called WikiDB – and an API operating thereon. Finally, the article provides an empirical study of using the three-fold representation format in conjunction with WikiDB.
@Article{Mehler:Gleim:Ernst:Waltinger:2008, Author = {Mehler, Alexander and Gleim, Rüdiger and Ernst, Alexandra and Waltinger, Ulli}, Title = {WikiDB: Building Interoperable Wiki-Based Knowledge Resources for Semantic Databases}, Journal = {Sprache und Datenverarbeitung. International Journal for Language Data Processing}, Volume = {32}, Number = {1}, Pages = {47-70}, abstract = {This article describes an API for exploring the logical document and the logical network structure of wikis. It introduces an algorithm for the semantic preprocessing, filtering and typing of these building blocks. Further, this article models the process of wiki generation based on a unified format of syntactic, semantic and pragmatic representations. This three-level approach to make accessible syntactic, semantic and pragmatic aspects of wiki-based structure formation is complemented by a corresponding database model – called WikiDB – and an API operating thereon. Finally, the article provides an empirical study of using the three-fold representation format in conjunction with WikiDB.}, pdf = {http://www.ulliwaltinger.de/pdf/Konvens_2008_WikiDB_Building_Semantic_Databases_MehlerGleimErnstWaltinger.pdf}, year = 2008 }
-
U. Waltinger and A. Mehler, "Who is it? Context sensitive named entity and instance recognition by means of Wikipedia," in Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence (WI-2008), 2008, p. 381–384.
[BibTeX]@InProceedings{Waltinger:Mehler:2008:a, Author = {Waltinger, Ulli and Mehler, Alexander}, Title = {Who is it? Context sensitive named entity and instance recognition by means of Wikipedia}, BookTitle = {Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence (WI-2008)}, Pages = {381–384}, Publisher = {IEEE Computer Society}, pdf = {http://www.ulliwaltinger.de/pdf/WI_2008_Context_Sensitive_Instance_Recognition_WaltingerMehler.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.5881}, year = 2008 }
-
A. Lücking, A. Mehler, and P. Menke, "Taking Fingerprints of Speech-and-Gesture Ensembles: Approaching Empirical Evidence of Intrapersonal Alignment in Multimodal Communication," in LONDIAL 2008: Proceedings of the 12th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL), King's College London, 2008, p. 157–164.
[BibTeX]@InProceedings{Luecking:Mehler:Menke:2008, Author = {Lücking, Andy and Mehler, Alexander and Menke, Peter}, Title = {Taking Fingerprints of Speech-and-Gesture Ensembles: Approaching Empirical Evidence of Intrapersonal Alignment in Multimodal Communication}, BookTitle = {LONDIAL 2008: Proceedings of the 12th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL)}, Pages = {157–164}, Address = {King's College London}, month = {June 2–4}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/luecking_mehler_menke_2008.pdf}, website = {https://www.researchgate.net/publication/237305375_Taking_Fingerprints_of_Speech-and-Gesture_Ensembles_Approaching_Empirical_Evidence_of_Intrapersonal_Alignment_in_Multimodal_Communication}, year = 2008 }
-
A. Mehler and T. Sutter, "Interaktive Textproduktion in Wiki-basierten Kommunikationssystemen," in Kommunikation, Partizipation und Wirkungen im Social Web – Weblogs, Wikis, Podcasts und Communities aus interdisziplinärer Sicht, A. Zerfaß, M. Welker, and J. Schmidt, Eds., Köln: Herbert von Halem, 2008, pp. 267-300.
[Abstract] [BibTeX]This article addresses challenges in maintaining and annotating image resources in the field of iconographic research. We focus on the task of bringing together generic and extensible techniques for resource and anno- tation management with the highly specific demands in this area of research. Special emphasis is put on the interrelation of images, image segements and textual contents. In addition, we describe the architecture, data model and user interface of the open annotation system used in the image database application that is a part of the eHumanities Desktop.
@InCollection{Mehler:Sutter:2008, Author = {Mehler, Alexander and Sutter, Tilmann}, Title = {Interaktive Textproduktion in Wiki-basierten Kommunikationssystemen}, BookTitle = {Kommunikation, Partizipation und Wirkungen im Social Web – Weblogs, Wikis, Podcasts und Communities aus interdisziplin{\"a}rer Sicht}, Publisher = {Herbert von Halem}, Editor = {Zerfa{\ss}, Ansgar and Welker, Martin and Schmidt, Jan}, Pages = {267-300}, Address = {Köln}, abstract = {This article addresses challenges in maintaining and annotating image resources in the field of iconographic research. We focus on the task of bringing together generic and extensible techniques for resource and anno- tation management with the highly specific demands in this area of research. Special emphasis is put on the interrelation of images, image segements and textual contents. In addition, we describe the architecture, data model and user interface of the open annotation system used in the image database application that is a part of the eHumanities Desktop.}, year = 2008 }
-
A. Mehler, "On the Impact of Community Structure on Self-Organizing Lexical Networks," in Proceedings of the 7th Evolution of Language Conference (Evolang 2008), March 11-15, 2008, Barcelona, 2008, pp. 227-234.
[Abstract] [BibTeX]This paper presents a simulation model of self-organizing lexical networks. Its starting point is the notion of an association game in which the impact of varying community models is studied on the emergence of lexical networks. The paper reports on experiments whose results are in accordance with findings in the framework of the naming game. This is done by means of a multilevel network model in which the correlation of social and of linguistic networks is studied
@InProceedings{Mehler:2008:e, Author = {Mehler, Alexander}, Title = {On the Impact of Community Structure on Self-Organizing Lexical Networks}, BookTitle = {Proceedings of the 7th Evolution of Language Conference (Evolang 2008), March 11-15, 2008, Barcelona}, Editor = {Smith, Andrew D. M. and Smith, Kenny and Cancho, Ramon Ferrer i}, Pages = {227-234}, Publisher = {World Scientific}, abstract = {This paper presents a simulation model of self-organizing lexical networks. Its starting point is the notion of an association game in which the impact of varying community models is studied on the emergence of lexical networks. The paper reports on experiments whose results are in accordance with findings in the framework of the naming game. This is done by means of a multilevel network model in which the correlation of social and of linguistic networks is studied}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2008_b.pdf}, website = {http://stel.ub.edu/evolang2008/evo10.htm}, year = 2008 }
-
O. Abramov and A. Mehler, "Towards a Uniform Representation of Treebanks: Providing Interoperability for Dependency Tree Data," in Proceedings of First International Conference on Global Interoperability for Language Resources (ICGL 2008), Hong Kong SAR, January 9-11, 2008.
[Abstract] [BibTeX]In this paper we present a corpus representation format which unifies the representation of a wide range of dependency treebanks within a single model. This approach provides interoperability and reusability of annotated syntactic data which in turn extends its applicability within various research contexts. We demonstrate our approach by means of dependency treebanks of 11 languages. Further, we perform a comparative quantitative analysis of these treebanks in order to demonstrate the interoperability of our approach.
@InProceedings{Pustylnikov:Mehler:2008:a, Author = {Abramov, Olga and Mehler, Alexander}, Title = {Towards a Uniform Representation of Treebanks: Providing Interoperability for Dependency Tree Data}, BookTitle = {Proceedings of First International Conference on Global Interoperability for Language Resources (ICGL 2008), Hong Kong SAR, January 9-11}, abstract = {In this paper we present a corpus representation format which unifies the representation of a wide range of dependency treebanks within a single model. This approach provides interoperability and reusability of annotated syntactic data which in turn extends its applicability within various research contexts. We demonstrate our approach by means of dependency treebanks of 11 languages. Further, we perform a comparative quantitative analysis of these treebanks in order to demonstrate the interoperability of our approach. }, pdf = {http://wwwhomes.uni-bielefeld.de/opustylnikov/pustylnikov/pdfs/acl07.1.0.pdf}, website = {https://www.researchgate.net/publication/242681771_Towards_a_Uniform_Representation_of_Treebanks_Providing_Interoperability_for_Dependency_Tree_Data}, year = 2008 }
-
G. Rehm, M. Santini, A. Mehler, P. Braslavski, R. Gleim, A. Stubbe, S. Symonenko, M. Tavosanis, and V. Vidulin, "Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems," in Proceedings of the 6th Language Resources and Evaluation Conference (LREC 2008), Marrakech (Morocco), 2008.
[Abstract] [BibTeX]We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres.
@InProceedings{Rehm:Santini:Mehler:Braslavski:Gleim:Stubbe:Symonenko:Tavosanis:Vidulin:2008, Author = {Rehm, Georg and Santini, Marina and Mehler, Alexander and Braslavski, Pavel and Gleim, Rüdiger and Stubbe, Andrea and Symonenko, Svetlana and Tavosanis, Mirko and Vidulin, Vedrana}, Title = {Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems}, BookTitle = {Proceedings of the 6th Language Resources and Evaluation Conference (LREC 2008), Marrakech (Morocco)}, abstract = {We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres. }, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/rehm_santini_mehler_braslavski_gleim_stubbe_symonenko_tavosanis_vidulin_2008.pdf}, website = {http://www.lrec-conf.org/proceedings/lrec2008/summaries/94.html}, year = 2008 }
2007 (29)
-
R. Gleim, A. Mehler, M. Dehmer, and O. Abramov, "Aisles through the Category Forest – Utilising the Wikipedia Category System for Corpus Building in Machine Learning," in 3rd International Conference on Web Information Systems and Technologies (WEBIST '07), March 3-6, 2007, Barcelona, Barcelona, 2007, pp. 142-149.
[Abstract] [BibTeX]The Word Wide Web is a continuous challenge to machine learning. Established approaches have to be enhanced and new methods be developed in order to tackle the problem of finding and organising relevant information. It has often been motivated that semantic classifications of input documents help solving this task. But while approaches of supervised text categorisation perform quite well on genres found in written text, newly evolved genres on the web are much more demanding. In order to successfully develop approaches to web mining, respective corpora are needed. However, the composition of genre- or domain-specific web corpora is still an unsolved problem. It is time consuming to build large corpora of good quality because web pages typically lack reliable meta information. Wikipedia along with similar approaches of collaborative text production offers a way out of this dilemma. We examine how social tagging, as supported by the MediaWiki software, can be utilised as a source of corpus building. Further, we describe a representation format for social ontologies and present the Wikipedia Category Explorer, a tool which supports categorical views to browse through the Wikipedia and to construct domain specific corpora for machine learning.
@InProceedings{Gleim:Mehler:Dehmer:Abramov:2007, Author = {Gleim, Rüdiger and Mehler, Alexander and Dehmer, Matthias and Abramov, Olga}, Title = {Aisles through the Category Forest – Utilising the Wikipedia Category System for Corpus Building in Machine Learning}, BookTitle = {3rd International Conference on Web Information Systems and Technologies (WEBIST '07), March 3-6, 2007, Barcelona}, Editor = {Filipe, Joaquim and Cordeiro, José and Encarnação, Bruno and Pedrosa, Vitor}, Pages = {142-149}, Address = {Barcelona}, abstract = {The Word Wide Web is a continuous challenge to machine learning. Established approaches have to be enhanced and new methods be developed in order to tackle the problem of finding and organising relevant information. It has often been motivated that semantic classifications of input documents help solving this task. But while approaches of supervised text categorisation perform quite well on genres found in written text, newly evolved genres on the web are much more demanding. In order to successfully develop approaches to web mining, respective corpora are needed. However, the composition of genre- or domain-specific web corpora is still an unsolved problem. It is time consuming to build large corpora of good quality because web pages typically lack reliable meta information. Wikipedia along with similar approaches of collaborative text production offers a way out of this dilemma. We examine how social tagging, as supported by the MediaWiki software, can be utilised as a source of corpus building. Further, we describe a representation format for social ontologies and present the Wikipedia Category Explorer, a tool which supports categorical views to browse through the Wikipedia and to construct domain specific corpora for machine learning.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2016/10/webist_2007-gleim_mehler_dehmer_pustylnikov.pdf}, year = 2007 }
-
A. Mehler, R. Gleim, and A. Wegner, "Structural Uncertainty of Hypertext Types. An Empirical Study," in Proceedings of the Workshop "Towards Genre-Enabled Search Engines: The Impact of NLP", September, 30, 2007, in conjunction with RANLP 2007, Borovets, Bulgaria, 2007, pp. 13-19.
[BibTeX]@InProceedings{Mehler:Gleim:Wegner:2007, Author = {Mehler, Alexander and Gleim, Rüdiger and Wegner, Armin}, Title = {Structural Uncertainty of Hypertext Types. An Empirical Study}, BookTitle = {Proceedings of the Workshop "Towards Genre-Enabled Search Engines: The Impact of NLP", September, 30, 2007, in conjunction with RANLP 2007, Borovets, Bulgaria}, Editor = {Rehm, Georg and Santini, Marina}, Pages = {13-19}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/RANLP.pdf}, year = 2007 }
-
A. Mehler, "Evolving Lexical Networks. A Simulation Model of Terminological Alignment," in Proceedings of the Workshop on Language, Games, and Evolution at the 9th European Summer School in Logic, Language and Information (ESSLLI 2007), Trinity College, Dublin, 6-17 August, 2007, pp. 57-67.
[Abstract] [BibTeX]In this paper we describe a simulation model of terminological alignment in a multiagent community. It is based on the notion of an association game which is used instead of the classical notion of a naming game (Steels, 1996). The simulation model integrates a small world-like agent community which restricts agent communication. We hypothesize that this restriction is decisive when it comes to simulate terminological alignment based on lexical priming. The paper presents preliminary experimental results in support of this hypothesis.
@InProceedings{Mehler:2007:d, Author = {Mehler, Alexander}, Title = {Evolving Lexical Networks. A Simulation Model of Terminological Alignment}, BookTitle = {Proceedings of the Workshop on Language, Games, and Evolution at the 9th European Summer School in Logic, Language and Information (ESSLLI 2007), Trinity College, Dublin, 6-17 August}, Editor = {Benz, Anton and Ebert, Christian and van Rooij, Robert}, Pages = {57-67}, abstract = {In this paper we describe a simulation model of terminological alignment in a multiagent community. It is based on the notion of an association game which is used instead of the classical notion of a naming game (Steels, 1996). The simulation model integrates a small world-like agent community which restricts agent communication. We hypothesize that this restriction is decisive when it comes to simulate terminological alignment based on lexical priming. The paper presents preliminary experimental results in support of this hypothesis.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2007_d.pdf}, year = 2007 }
-
A. Mehler, P. Geibel, R. Gleim, S. Herold, B. Jain, and O. Abramov, "Much Ado About Text Content. Learning Text Types Solely by Structural Differentiae," in Proceedings of OTT '06 – Ontologies in Text Technology: Approaches to Extract Semantic Knowledge from Structured Information, Osnabrück, 2007, pp. 63-71.
[Abstract] [BibTeX]In this paper, we deal with classifying texts into classes which denote text types whose textual instances serve more or less homogeneous functions. Other than mainstream approaches to text classification, which rely on the vector space model [30] or some of its descendants [2] and, thus, on content-related lexical features, we solely refer to structural differentiae, that is, to patterns of text structure as determinants of class membership. Further, we suppose that text types span a type hierarchy based on the type-subtype relation [31]. Thus, although we admit that class membership is fuzzy so that overlapping classes are inevitable, we suppose a non-overlapping type system structured into a rooted tree – whether solely based on functional or additional on, e.g., content- or mediabased criteria [1]. What regards criteria of goodness of classification, we perform a classical supervised categorization experiment [30] based on cross-validation as a method of model selection [11]. That is, we perform a categorization experiment in which for all training and test cases class membership is known ex ante. In summary, we perform a supervised experiment of text classification in order to learn functionally grounded text types where membership to these types is solely based on structural criteria.
@InProceedings{Mehler:Geibel:Gleim:Herold:Jain:Pustylnikov:2007, Author = {Mehler, Alexander and Geibel, Peter and Gleim, Rüdiger and Herold, Sebastian and Jain, Brijnesh-Johannes and Abramov, Olga}, Title = {Much Ado About Text Content. Learning Text Types Solely by Structural Differentiae}, BookTitle = {Proceedings of OTT '06 – Ontologies in Text Technology: Approaches to Extract Semantic Knowledge from Structured Information}, Editor = {Mönnich, Uwe and Kühnberger, Kai-Uwe}, Series = {Publications of the Institute of Cognitive Science (PICS)}, Pages = {63-71}, Address = {Osnabrück}, abstract = {In this paper, we deal with classifying texts into classes which denote text types whose textual instances serve more or less homogeneous functions. Other than mainstream approaches to text classification, which rely on the vector space model [30] or some of its descendants [2] and, thus, on content-related lexical features, we solely refer to structural differentiae, that is, to patterns of text structure as determinants of class membership. Further, we suppose that text types span a type hierarchy based on the type-subtype relation [31]. Thus, although we admit that class membership is fuzzy so that overlapping classes are inevitable, we suppose a non-overlapping type system structured into a rooted tree – whether solely based on functional or additional on, e.g., content- or mediabased criteria [1]. What regards criteria of goodness of classification, we perform a classical supervised categorization experiment [30] based on cross-validation as a method of model selection [11]. That is, we perform a categorization experiment in which for all training and test cases class membership is known ex ante. In summary, we perform a supervised experiment of text classification in order to learn functionally grounded text types where membership to these types is solely based on structural criteria.}, pdf = {http://ikw.uni-osnabrueck.de/~ott06/ott06-abstracts/Mehler_Geibel_abstract.pdf}, year = 2007 }
-
M. Dehmer, A. Mehler, and F. Emmert-Streib, "Graph-theoretical Characterizations of Generalized Trees," in Proceedings of the 2007 International Conference on Machine Learning: Models, Technologies & Applications (MLMTA '07), June 25-28, 2007, Las Vegas, 2007, pp. 113-117.
[BibTeX]@InProceedings{Dehmer:Mehler:Emmert-Streib:2007:a, Author = {Dehmer, Matthias and Mehler, Alexander and Emmert-Streib, Frank}, Title = {Graph-theoretical Characterizations of Generalized Trees}, BookTitle = {Proceedings of the 2007 International Conference on Machine Learning: Models, Technologies \& Applications (MLMTA '07), June 25-28, 2007, Las Vegas}, Pages = {113-117}, website = {https://www.researchgate.net/publication/221188591_Graph-theoretical_Characterizations_of_Generalized_Trees}, year = 2007 }
-
R. Gleim, A. Mehler, and H. Eikmeyer, "Representing and Maintaining Large Corpora," in Proceedings of the Corpus Linguistics 2007 Conference, Birmingham (UK), 2007.
[BibTeX]@InProceedings{Gleim:Mehler:Eikmeyer:2007:a, Author = {Gleim, Rüdiger and Mehler, Alexander and Eikmeyer, Hans-Jürgen}, Title = {Representing and Maintaining Large Corpora}, BookTitle = {Proceedings of the Corpus Linguistics 2007 Conference, Birmingham (UK)}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gleim_mehler_eikmeyer_2007_a.pdf}, year = 2007 }
-
P. Geibel, O. Abramov, A. Mehler, H. Gust, and K. Kühnberger, "Classification of Documents Based on the Structure of Their DOM Trees," in Proceedings of ICONIP 2007 (14th International Conference on Neural Information Processing), 2007, p. 779–788.
[Abstract] [BibTeX]In this paper, we discuss kernels that can be applied for the classification of XML documents based on their DOM trees. DOM trees are ordered trees in which every node might be labeled by a vector of attributes including its XML tag and the textual content. We describe five new kernels suitable for such structures: a kernel based on predefined structural features, a tree kernel derived from the well-known parse tree kernel, the set tree kernel that allows permutations of children, the string tree kernel being an extension of the so-called partial tree kernel, and the soft tree kernel as a more efficient alternative. We evaluate the kernels experimentally on a corpus containing the DOM trees of newspaper articles and on the well-known SUSANNE corpus.
@InProceedings{Geibel:Pustylnikov:Mehler:Gust:Kuehnberger:2007, Author = {Geibel, Peter and Abramov, Olga and Mehler, Alexander and Gust, Helmar and Kühnberger, Kai-Uwe}, Title = {Classification of Documents Based on the Structure of Their DOM Trees}, BookTitle = {Proceedings of ICONIP 2007 (14th International Conference on Neural Information Processing)}, Series = {Lecture Notes in Computer Science 4985}, Pages = {779–788}, Publisher = {Springer}, abstract = {In this paper, we discuss kernels that can be applied for the classification of XML documents based on their DOM trees. DOM trees are ordered trees in which every node might be labeled by a vector of attributes including its XML tag and the textual content. We describe five new kernels suitable for such structures: a kernel based on predefined structural features, a tree kernel derived from the well-known parse tree kernel, the set tree kernel that allows permutations of children, the string tree kernel being an extension of the so-called partial tree kernel, and the soft tree kernel as a more efficient alternative. We evaluate the kernels experimentally on a corpus containing the DOM trees of newspaper articles and on the well-known SUSANNE corpus.}, website = {http://www.springerlink.com/content/x414002113425742/}, year = 2007 }
-
B. Jussen, A. Mehler, and A. Ernst, "A Corpus Management System for Historical Semantics," Sprache und Datenverarbeitung. International Journal for Language Data Processing, vol. 31, iss. 1-2, pp. 81-89, 2007.
[Abstract] [BibTeX]Der Beitrag beschreibt ein Korpusmanagementsystem für die historische Semantik. Die Grundlage hierfür bildet ein Bedeutungsbegriff, der – methodologisch gesprochen – auf der Analyse diachroner Korpora beruht. Das Ziel der Analyse dieser Korpora besteht darin, Bedeutungswandel als eine Bezugsgröße für den Wandel sozialer Systeme zu untersuchen. Das vorgestellte Korpusmanagementsystem unterstützt diese Art der korpusbasierten historischen Semantik.
@Article{Jussen:Mehler:Ernst:2007, Author = {Jussen, Bernhard and Mehler, Alexander and Ernst, Alexandra}, Title = {A Corpus Management System for Historical Semantics}, Journal = {Sprache und Datenverarbeitung. International Journal for Language Data Processing}, Volume = {31}, Number = {1-2}, Pages = {81-89}, abstract = {Der Beitrag beschreibt ein Korpusmanagementsystem für die historische Semantik. Die Grundlage hierfür bildet ein Bedeutungsbegriff, der – methodologisch gesprochen – auf der Analyse diachroner Korpora beruht. Das Ziel der Analyse dieser Korpora besteht darin, Bedeutungswandel als eine Bezugsgrö{\ss}e für den Wandel sozialer Systeme zu untersuchen. Das vorgestellte Korpusmanagementsystem unterstützt diese Art der korpusbasierten historischen Semantik.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/jussen_mehler_ernst_2007.pdf}, year = 2007 }
-
A. Mehler and R. Köhler, "Machine Learning in a Semiotic Perspective," in Aspects of Automatic Text Analysis, A. Mehler and R. Köhler, Eds., Berlin/New York: Springer, 2007, pp. 1-29.
[Abstract] [BibTeX]Gegenstand des folgenden Aufsatzes ist der konnotative Aspekt der Bedeutungen von Texten. Den Ausgangspunkt der Überlegungen zur Konnotation des Textes bildet die Auffassung, wonach Wort- und Textbedeutungskonstitution Ergebnis eines zirkulären Prozesses sind, der für die Emergenz einer Hierarchie ineinander geschachtelter Spracheinheiten verantwortlich zeichnet. Der Prozeß der Zeichenartikulation erfolgt entlang dieser Ebenen und erzeugt durch Verbindung von (konnotativer) Inhalts- und Ausdrucksseite auf Textebene das Textzeichen. Im Gegensatz zu einer strikten Interpretation des Fregeschen Kompositionalitätsprinzips, derzufolge die Bedeutungen sprachlicher Einheiten als fixierte, kontextfreie Größen vorauszusetzen sind, behandelt der vorliegende Ansatz bereits die lexikalische Bedeutung als Größe, die in Abhängigkeit von ihrem Kontext variieren kann. Aus semiotischer Perspektive ist es vor allem der Gestaltcharakter, welcher die konnotative Textbedeutung einer Anwendung des FregePrinzips entzieht. Anders ausgedrückt: Die konnotative Bedeutung eines Textes ist keineswegs in eine Struktur 'atomarer' Repräsentationen zerlegbar. Die hierarchische Organisation von Texten erweist sich insofern als komplex, als ihre Bedeutungen aus einem zirkulären Prozeß resultieren, der bestätigend und/oder verändernd auf die Bedeutungen der Textkonstituenten einwirkt. Diese Zirkularität bedingt, daß Texte nicht nur als Orte der Manifestation von Wortbedeutungsstrukturen anzusehen sind, sondern zugleich als Ausgangspunkte für die Modifikation und Emergenz solcher Strukturen dienen. Im folgenden wird unter Rekurs auf den Kopenhagener Strukturalismus ein Modell der konnotativen Bedeutung von Texten entwickelt, das sich unter anderem an dem glossematischen Begriff der Konstante orientiert. Die Formalisierung des Modells erfolgt mit Hilfe des Konzeptes der unscharfen Menge. Zu diesem Zweck werden die unscharfen Verwendungsregularitäten von Wörtern auf der Basis eines zweistufigen Verfahrens analysiert, welches die syntagmatischen und paradigmatischen Regularitäten des Wortgebrauches berücksichtigt. Die Rolle der Satzebene innerhalb des Prozesses der konnotativen Textbedeutungskonstitution wird angedeutet. Abschließend erfolgt eine Exemplifizierung des Algorithmus anhand der automatischen Analyse eines Textcorpus.
@InCollection{Mehler:Koehler:2007:b, Author = {Mehler, Alexander and Köhler, Reinhard}, Title = {Machine Learning in a Semiotic Perspective}, BookTitle = {Aspects of Automatic Text Analysis}, Publisher = {Springer}, Editor = {Mehler, Alexander and Köhler, Reinhard}, Series = {Studies in Fuzziness and Soft Computing}, Pages = {1-29}, Address = {Berlin/New York}, abstract = {Gegenstand des folgenden Aufsatzes ist der konnotative Aspekt der Bedeutungen von Texten. Den Ausgangspunkt der {\"U}berlegungen zur Konnotation des Textes bildet die Auffassung, wonach Wort- und Textbedeutungskonstitution Ergebnis eines zirkul{\"a}ren Prozesses sind, der für die Emergenz einer Hierarchie ineinander geschachtelter Spracheinheiten verantwortlich zeichnet. Der Proze{\ss} der Zeichenartikulation erfolgt entlang dieser Ebenen und erzeugt durch Verbindung von (konnotativer) Inhalts- und Ausdrucksseite auf Textebene das Textzeichen. Im Gegensatz zu einer strikten Interpretation des Fregeschen Kompositionalit{\"a}tsprinzips, derzufolge die Bedeutungen sprachlicher Einheiten als fixierte, kontextfreie Grö{\ss}en vorauszusetzen sind, behandelt der vorliegende Ansatz bereits die lexikalische Bedeutung als Grö{\ss}e, die in Abh{\"a}ngigkeit von ihrem Kontext variieren kann. Aus semiotischer Perspektive ist es vor allem der Gestaltcharakter, welcher die konnotative Textbedeutung einer Anwendung des FregePrinzips entzieht. Anders ausgedrückt: Die konnotative Bedeutung eines Textes ist keineswegs in eine Struktur 'atomarer' Repr{\"a}sentationen zerlegbar. Die hierarchische Organisation von Texten erweist sich insofern als komplex, als ihre Bedeutungen aus einem zirkul{\"a}ren Proze{\ss} resultieren, der best{\"a}tigend und/oder ver{\"a}ndernd auf die Bedeutungen der Textkonstituenten einwirkt. Diese Zirkularit{\"a}t bedingt, da{\ss} Texte nicht nur als Orte der Manifestation von Wortbedeutungsstrukturen anzusehen sind, sondern zugleich als Ausgangspunkte für die Modifikation und Emergenz solcher Strukturen dienen. Im folgenden wird unter Rekurs auf den Kopenhagener Strukturalismus ein Modell der konnotativen Bedeutung von Texten entwickelt, das sich unter anderem an dem glossematischen Begriff der Konstante orientiert. Die Formalisierung des Modells erfolgt mit Hilfe des Konzeptes der unscharfen Menge. Zu diesem Zweck werden die unscharfen Verwendungsregularit{\"a}ten von Wörtern auf der Basis eines zweistufigen Verfahrens analysiert, welches die syntagmatischen und paradigmatischen Regularit{\"a}ten des Wortgebrauches berücksichtigt. Die Rolle der Satzebene innerhalb des Prozesses der konnotativen Textbedeutungskonstitution wird angedeutet. Abschlie{\ss}end erfolgt eine Exemplifizierung des Algorithmus anhand der automatischen Analyse eines Textcorpus.}, website = {http://rd.springer.com/chapter/10.1007/978-3-540-37522-7_1}, year = 2007 }
-
A. Mehler, U. Waltinger, and A. Wegner, "A Formal Text Representation Model Based on Lexical Chaining," in Proceedings of the KI 2007 Workshop on Learning from Non-Vectorial Data (LNVD 2007) September 10, Osnabrück, Osnabrück, 2007, pp. 17-26.
[Abstract] [BibTeX]This paper presents a formal text representation model as an alternative to the vector space model. It combines a tree-like model with graph-inducing lexical relations. The paper aims at formalizing two yet unrelated approaches, i.e. lexical chaining [3] and quantitative structure analysis [9], in order to combine content and structure modeling.
@InProceedings{Mehler:Waltinger:Wegner:2007:a, Author = {Mehler, Alexander and Waltinger, Ulli and Wegner, Armin}, Title = {A Formal Text Representation Model Based on Lexical Chaining}, BookTitle = {Proceedings of the KI 2007 Workshop on Learning from Non-Vectorial Data (LNVD 2007) September 10, Osnabrück}, Editor = {Geibel, Peter and Jain, Brijnesh J.}, Pages = {17-26}, Address = {Osnabrück}, Publisher = {Universit{\"a}t Osnabrück}, abstract = {This paper presents a formal text representation model as an alternative to the vector space model. It combines a tree-like model with graph-inducing lexical relations. The paper aims at formalizing two yet unrelated approaches, i.e. lexical chaining [3] and quantitative structure analysis [9], in order to combine content and structure modeling.}, pdf = {http://www.ulliwaltinger.de/pdf/LNVD07MehlerWaltingerWegner.pdf}, year = 2007 }
-
T. vor der Brück and S. Hartrumpf, "A Semantically Oriented Readability Checker for German," in Proceedings of the 3rd Language & Technology Conference, Z. Vetulani, Ed., Poznań, Poland: Wydawnictwo Poznańskie, 2007, pp. 270-274.
[Abstract] [BibTeX]One major reason that readability checkers are still far away from judging the understandability of texts consists in the fact that no semantic information is used. Syntactic, lexical, or morphological information can only give limited access for estimating the cognitive difficulties for a human being to comprehend a text. In this paper however, we present a readability checker which uses semantic information in addition. This information is represented as semantic networks and is derived by a deep syntactico-semantic analysis. We investigate in which situations a semantic readability indicator can lead to superior results in comparison with ordinary surface indicators like sentence length. Finally, we compute the correlations and absolute errors for our semantic indicators related to user ratings collected in an online evaluation.
@InCollection{vor:der:Brueck:Hartrumpf:2007, Author = {vor der Brück, Tim and Hartrumpf, Sven}, Title = {A Semantically Oriented Readability Checker for German}, BookTitle = {Proceedings of the 3rd Language \& Technology Conference}, Publisher = {Wydawnictwo Poznańskie}, Editor = {Zygmunt Vetulani}, Pages = {270--274}, Address = {Poznań, Poland}, abstract = {One major reason that readability checkers are still far away from judging the understandability of texts consists in the fact that no semantic information is used. Syntactic, lexical, or morphological information can only give limited access for estimating the cognitive difficulties for a human being to comprehend a text. In this paper however, we present a readability checker which uses semantic information in addition. This information is represented as semantic networks and is derived by a deep syntactico-semantic analysis. We investigate in which situations a semantic readability indicator can lead to superior results in comparison with ordinary surface indicators like sentence length. Finally, we compute the correlations and absolute errors for our semantic indicators related to user ratings collected in an online evaluation.}, isbn = {978-83-7177-407-2}, month = {October}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/brueck_hartrumpf07_online.pdf}, url = {http://pi7.fernuni-hagen.de/papers/brueck_hartrumpf07_online.pdf}, year = 2007 }
-
T. vor der Brück and S. Busemann, "Suggesting Error Corrections of Path Expressions and Categories for Tree-Mapping Grammars," Zeitschrift für Sprachwissenschaft, vol. 26, iss. 2, 2007.
[Abstract] [BibTeX]Tree mapping grammars are used in natural language generation (NLG) to map non-linguistic input onto a derivation tree from which the target text can be trivially read off as the terminal yield. Such grammars may consist of a large number of rules. Finding errors is quite tedious and sometimes very time-consuming. Often the generation fails because the relevant input subtree is not specified correctly. This work describes a method to detect and correct wrong assignments of input subtrees to grammar categories by cross-validating grammar rules with the given input structures. The method also detects and corrects the usage of a category in a grammar rule. The result is implemented in a grammar development workbench and accelerates the grammar writer's work considerably. The paper suggests the algorithms can be ported to other areas in which tree mapping is required.
@Article{vor:der:Brueck:Busemann:2007, Author = {vor der Brück, Tim and Busemann, Stephan}, Title = {Suggesting Error Corrections of Path Expressions and Categories for Tree-Mapping Grammars}, Journal = {Zeitschrift für Sprachwissenschaft}, Volume = {26}, Number = {2}, abstract = {Tree mapping grammars are used in natural language generation (NLG) to map non-linguistic input onto a derivation tree from which the target text can be trivially read off as the terminal yield. Such grammars may consist of a large number of rules. Finding errors is quite tedious and sometimes very time-consuming. Often the generation fails because the relevant input subtree is not specified correctly. This work describes a method to detect and correct wrong assignments of input subtrees to grammar categories by cross-validating grammar rules with the given input structures. The method also detects and corrects the usage of a category in a grammar rule. The result is implemented in a grammar development workbench and accelerates the grammar writer's work considerably. The paper suggests the algorithms can be ported to other areas in which tree mapping is required.}, url = {http://www.reference-global.com/doi/pdfplus/10.1515/ZFS.2007.021}, year = 2007 }
-
T. vor der Brück and J. Leveling, "Parameter Learning for a Readability Checking Tool," in Proceedings of the LWA 2007 (Lernen-Wissen-Adaption), Workshop KDML, A. Hinneburg, Ed., Halle/Saale, Germany: Gesellschaft für Informatik, 2007.
[Abstract] [BibTeX]This paper describes the application of machine learning methods to determine parameters for DeLite, a readability checking tool. DeLite pinpoints text segments that are difficult to understand and computes for a given text a global readability score, which is a weighted sum of normalized indicator values. Indicator values are numeric properties derived from linguistic units in the text, such as the distance between a verb and its complements or the number of possible antecedents for a pronoun. Indicators are normalized by means of a derivation of the Fermi function with two parameters. DeLite requires individual parameters for this normalization function and a weight for each indicator to compute the global readability score. Several experiments to determine these parameters were conducted, using different machine learning approaches. The training data consists of more than 300 user ratings of texts from the municipality domain. The weights for the indicators are learned using two approaches: i) robust regression with linear optimization and ii) an approximative iterative linear regression algorithm. For evaluation, the computed readability scores are compared to user ratings. The evaluation showed that iterative linear regression yields a smaller square error than robust regression although this method is only approximative. Both methods yield results outperforming a first manual setting, and for both methods, basically the same set of non-zero weights remain.
@InCollection{vor:der:Brueck:Leveling:2007, Author = {vor der Brück, Tim and Leveling, Johannes}, Title = {Parameter Learning for a Readability Checking Tool}, BookTitle = {Proceedings of the LWA 2007 (Lernen-Wissen-Adaption), Workshop KDML}, Publisher = {Gesellschaft für Informatik}, Editor = {Alexander Hinneburg}, Address = {Halle/Saale, Germany}, abstract = {This paper describes the application of machine learning methods to determine parameters for DeLite, a readability checking tool. DeLite pinpoints text segments that are difficult to understand and computes for a given text a global readability score, which is a weighted sum of normalized indicator values. Indicator values are numeric properties derived from linguistic units in the text, such as the distance between a verb and its complements or the number of possible antecedents for a pronoun. Indicators are normalized by means of a derivation of the Fermi function with two parameters. DeLite requires individual parameters for this normalization function and a weight for each indicator to compute the global readability score. Several experiments to determine these parameters were conducted, using different machine learning approaches. The training data consists of more than 300 user ratings of texts from the municipality domain. The weights for the indicators are learned using two approaches: i) robust regression with linear optimization and ii) an approximative iterative linear regression algorithm. For evaluation, the computed readability scores are compared to user ratings. The evaluation showed that iterative linear regression yields a smaller square error than robust regression although this method is only approximative. Both methods yield results outperforming a first manual setting, and for both methods, basically the same set of non-zero weights remain.}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.6079}, year = 2007 }
-
C. Borr, M. Hielscher-Fastabend, and A. Lücking, "Reliability and Validity of Cervical Auscultation," Dysphagia, vol. 22, pp. 225-234, 2007.
[Abstract] [BibTeX]We conducted a two-part study that contributes to the discussion about cervical auscultation (CA) as a scientifically justifiable and medically useful tool to identify patients with a high risk of aspiration/penetration. We sought to determine (1) acoustic features that mark a deglutition act as dysphagic; (2) acoustic changes in healthy older deglutition profiles compared with those of younger adults; (3) the correctness and concordance of rater judgments based on CA; and (4) if education in CA improves individual reliability. The first part of the study focused on a comparison of the swallow morphology of dysphagic as opposed to healthy subjects� deglutition in terms of structure properties of the pharyngeal phase of deglutition. We obtained the following results. The duration of deglutition apnea is significantly higher in the older group than in the younger one. Comparing the younger group and the dysphagic group we found significant differences in duration of deglutition apnea, onset time, and number of gulps. Just one parameter, number of gulps, distinguishes significantly between the older and the dysphagic groups. The second part of the study aimed at evaluating the reliability of CA in detecting dysphagia measured as the concordance and the correctness of CA experts in classifying swallowing sounds. The interrater reliability coefficient AC1 resulted in a value of 0.46, which is to be interpreted as fair agreement. Furthermore, we found that comparison with radiologically defined aspiration/penetration for the group of experts (speech and language therapists) yielded 70% specificity and 94% sensitivity. We conclude that the swallowing sounds contain audible cues that should, in principle, permit reliable classification and view CA as an early warning system for identifying patients with a high risk of aspiration/penetration; however, it is not appropriate as a stand-alone tool.
@Article{Borr:Luecking:Hierlscher:2007, Author = {Borr, Christiane and Hielscher-Fastabend, Martina and Lücking, Andy}, Title = {Reliability and Validity of Cervical Auscultation}, Journal = {Dysphagia}, Volume = {22}, Pages = {225--234}, abstract = {We conducted a two-part study that contributes to the discussion about cervical auscultation (CA) as a scientifically justifiable and medically useful tool to identify patients with a high risk of aspiration/penetration. We sought to determine (1) acoustic features that mark a deglutition act as dysphagic; (2) acoustic changes in healthy older deglutition profiles compared with those of younger adults; (3) the correctness and concordance of rater judgments based on CA; and (4) if education in CA improves individual reliability. The first part of the study focused on a comparison of the swallow morphology of dysphagic as opposed to healthy subjects� deglutition in terms of structure properties of the pharyngeal phase of deglutition. We obtained the following results. The duration of deglutition apnea is significantly higher in the older group than in the younger one. Comparing the younger group and the dysphagic group we found significant differences in duration of deglutition apnea, onset time, and number of gulps. Just one parameter, number of gulps, distinguishes significantly between the older and the dysphagic groups. The second part of the study aimed at evaluating the reliability of CA in detecting dysphagia measured as the concordance and the correctness of CA experts in classifying swallowing sounds. The interrater reliability coefficient AC1 resulted in a value of 0.46, which is to be interpreted as fair agreement. Furthermore, we found that comparison with radiologically defined aspiration/penetration for the group of experts (speech and language therapists) yielded 70% specificity and 94% sensitivity. We conclude that the swallowing sounds contain audible cues that should, in principle, permit reliable classification and view CA as an early warning system for identifying patients with a high risk of aspiration/penetration; however, it is not appropriate as a stand-alone tool.}, doi = {10.1007/s00455-007-9078-3}, issue = {3}, pdf = {http://www.shkim.eu/cborr/ca5manuscript.pdf}, publisher = {Springer New York}, url = {http://dx.doi.org/10.1007/s00455-007-9078-3}, website = {http://www.springerlink.com/content/c45578u74r38m4v7/}, year = 2007 }
-
A. Kranstedt, A. Lücking, T. Pfeiffer, H. Rieser, and M. Staudacher, Locating Objects by Pointing, 2007.
[BibTeX]@Misc{Kranstedt:et:al:2007, Author = {Kranstedt, Alfred and Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes and Staudacher, Marc}, Title = {Locating Objects by Pointing}, HowPublished = {3rd International Conference of the International Society for Gesture Studies. Evanston, IL, USA}, keywords = {own}, month = {6}, year = 2007 }
-
M. Asadullah, M. Z. Islam, and M. Khan, "Error-tolerant Finite-state Recognizer and String Pattern Similarity Based Spell-Checker for Bengali," in 5th International Conference on Natural Language Processing (ICON) as a poster,Hyderabad, India, January 2007, 2007.
[Abstract] [BibTeX]A crucial figure of merit for a spelling checker is not just whether it can detect misspelled words, but also in how it ranks the sugges tions for the word. Spelling checker algorithms using edit distance methods tend to produce a large number of possibilities for misspelled words. We propose an alternative approach to checking the spelling of Bangla text that uses a finite state automaton (FSA) to probabilistically create the suggestion list for a misspelled word. FSA has proven to be an effective method for problems requiring probabilistic solution and high error tolerance. We start by using a finite state representation for all the words in the Bangla dictionary; the algorithm then uses the state tables to test a string, and in case of an erroneous string, try to find all possible solutions by attempting singular and multi - step transitions to consume one or more characters and using the su bsequent characters as look - ahead; and finally, we use backtracking to add each possible solution to the suggestion list. The use of finite state representation for the word implies that the algorithm is much more efficient in the case of non - inflected for ms; in case of nouns, it is even more significant as Bangla nouns are heavily used in the non - inflected form. In terms of error detection and correction, the algorithm uses the statistics of Bangla error pattern and thus produces a small number of signific ant suggestions. One notable limitation is the inability to handle transposition errors as a single edit distance errors. This is not as significant as it may seem since the number of transposition errors are not as common as other errors in Bangla. This p aper presents the structure and the algorithm to implement a Practical Bangla spell - checker, and discusses the results obtained from the prototype implementation.
@InProceedings{Asadullah:Zahurul:Khan:2007, Author = {Asadullah, Munshi and Islam, Md. Zahurul and Khan, Mumit}, Title = {Error-tolerant Finite-state Recognizer and String Pattern Similarity Based Spell-Checker for Bengali}, BookTitle = {5th International Conference on Natural Language Processing (ICON) as a poster,Hyderabad, India, January 2007}, abstract = {A crucial figure of merit for a spelling checker is not just whether it can detect misspelled words, but also in how it ranks the sugges tions for the word. Spelling checker algorithms using edit distance methods tend to produce a large number of possibilities for misspelled words. We propose an alternative approach to checking the spelling of Bangla text that uses a finite state automaton (FSA) to probabilistically create the suggestion list for a misspelled word. FSA has proven to be an effective method for problems requiring probabilistic solution and high error tolerance. We start by using a finite state representation for all the words in the Bangla dictionary; the algorithm then uses the state tables to test a string, and in case of an erroneous string, try to find all possible solutions by attempting singular and multi - step transitions to consume one or more characters and using the su bsequent characters as look - ahead; and finally, we use backtracking to add each possible solution to the suggestion list. The use of finite state representation for the word implies that the algorithm is much more efficient in the case of non - inflected for ms; in case of nouns, it is even more significant as Bangla nouns are heavily used in the non - inflected form. In terms of error detection and correction, the algorithm uses the statistics of Bangla error pattern and thus produces a small number of signific ant suggestions. One notable limitation is the inability to handle transposition errors as a single edit distance errors. This is not as significant as it may seem since the number of transposition errors are not as common as other errors in Bangla. This p aper presents the structure and the algorithm to implement a Practical Bangla spell - checker, and discusses the results obtained from the prototype implementation.}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Error-tolerant_Finite-state_Recognizer_and_String_Pattern_Similarity_Based_Spell-Checker_for_Bengali.pdf}, timestamp = {2011.08.02}, year = 2007 }
-
M. Z. Islam, M. N. Uddin, and M. Khan, "A Light Weight Stemmer for Bengali and Its Use in Spelling Checker," in 1st International Conference on Digital Communications and Computer Applications (DCCA2007), 2007.
[Abstract] [BibTeX]Stemming is an operation that splits a word into the constituent root part and affix without doing complete morphological analysis. It is used to impr ove the performance of spelling checkers and informatio n retrieval applications, where morphological analysi would be too computationally expensive. For spellin g checkers specifically, using stemming may drastical ly reduce the dictionary size, often a bottleneck for mobile and embedded devices. This paper presents a computationally inexpensive stemming algorithm for Bengali, which handles suffix removal in a domain independent way. The evaluation of the proposed algorithm in a Bengali spelling checker indicates t hat it can be effectively used in information retrieval applications in general.
@InProceedings{Zahurul:Uddin:Khan:2007, Author = {Islam, Md. Zahurul and Uddin, Md. Nizam and Khan, Mumit}, Title = {A Light Weight Stemmer for Bengali and Its Use in Spelling Checker}, BookTitle = {1st International Conference on Digital Communications and Computer Applications (DCCA2007)}, abstract = {Stemming is an operation that splits a word into the constituent root part and affix without doing complete morphological analysis. It is used to impr ove the performance of spelling checkers and informatio n retrieval applications, where morphological analysi would be too computationally expensive. For spellin g checkers specifically, using stemming may drastical ly reduce the dictionary size, often a bottleneck for mobile and embedded devices. This paper presents a computationally inexpensive stemming algorithm for Bengali, which handles suffix removal in a domain independent way. The evaluation of the proposed algorithm in a Bengali spelling checker indicates t hat it can be effectively used in information retrieval applications in general.}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/A_Light_Weight_Stemmer_for_Bengali_and_Its_Use_in_Spelling_Checker.pdf}, timestamp = {2011.08.02}, year = 2007 }
-
M. Z. Islam and M. Khan, "Bangla Verb Morphology and a Multilingual Computational Morphology FrameWork for PC-KIMMO," in The Proceedings of Workshop on Morpho - Syntactic Analysis by the School of Asian Applied Natural Language Processing for Language Diversity and Language Resource Development (ADD), Bangkok, Thailand, 2007.
[BibTeX]@InProceedings{Zahurul:Khan:2007, Author = {Islam, Md. Zahurul and Khan, Mumit}, Title = {Bangla Verb Morphology and a Multilingual Computational Morphology FrameWork for PC-KIMMO}, BookTitle = {The Proceedings of Workshop on Morpho - Syntactic Analysis by the School of Asian Applied Natural Language Processing for Language Diversity and Language Resource Development (ADD), Bangkok, Thailand}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Bangla_Verb_Morphology_and_a_Multilingual_Computational_Morphology_FrameWork_for_PC-KIMMO-talk.pdf}, timestamp = {2011.08.02}, year = 2007 }
-
A. Mehler, P. Geibel, and O. Abramov, "Structural Classifiers of Text Types: Towards a Novel Model of Text Representation," Journal for Language Technology and Computational Linguistics (JLCL), vol. 22, iss. 2, pp. 51-66, 2007.
[Abstract] [BibTeX]Texts can be distinguished in terms of their content, function, structure or layout (Brinker, 1992; Bateman et al., 2001; Joachims, 2002; Power et al., 2003). These reference points do not open necessarily orthogonal perspectives on text classification. As part of explorative data analysis, text classification aims at automatically dividing sets of textual objects into classes of maximum internal homogeneity and external heterogeneity. This paper deals with classifying texts into text types whose instances serve more or less homogeneous functions. Other than mainstream approaches, which rely on the vector space model (Sebastiani, 2002) or some of its descendants (Baeza-Yates and Ribeiro-Neto, 1999) and, thus, on content-related lexical features, we solely refer to structural differentiae. That is, we explore patterns of text structure as determinants of class membership. Our starting point are tree-like text representations which induce feature vectors and tree kernels. These kernels are utilized in supervised learning based on cross-validation as a method of model selection (Hastie et al., 2001) by example of a corpus of press communication. For a subset of categories we show that classification can be performed very well by structural differentia only.
@Article{Mehler:Geibel:Pustylnikov:2007, Author = {Mehler, Alexander and Geibel, Peter and Abramov, Olga}, Title = {Structural Classifiers of Text Types: Towards a Novel Model of Text Representation}, Journal = {Journal for Language Technology and Computational Linguistics (JLCL)}, Volume = {22}, Number = {2}, Pages = {51-66}, abstract = {Texts can be distinguished in terms of their content, function, structure or layout (Brinker, 1992; Bateman et al., 2001; Joachims, 2002; Power et al., 2003). These reference points do not open necessarily orthogonal perspectives on text classification. As part of explorative data analysis, text classification aims at automatically dividing sets of textual objects into classes of maximum internal homogeneity and external heterogeneity. This paper deals with classifying texts into text types whose instances serve more or less homogeneous functions. Other than mainstream approaches, which rely on the vector space model (Sebastiani, 2002) or some of its descendants (Baeza-Yates and Ribeiro-Neto, 1999) and, thus, on content-related lexical features, we solely refer to structural differentiae. That is, we explore patterns of text structure as determinants of class membership. Our starting point are tree-like text representations which induce feature vectors and tree kernels. These kernels are utilized in supervised learning based on cross-validation as a method of model selection (Hastie et al., 2001) by example of a corpus of press communication. For a subset of categories we show that classification can be performed very well by structural differentia only.}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_geibel_pustylnikov_2007.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.604}, year = 2007 }
-
O. Abramov and A. Mehler, "Structural Differentiae of Text Types. A Quantitative Model," in Proceedings of the 31st Annual Conference of the German Classification Society on Data Analysis, Machine Learning, and Applications (GfKl), 2007, p. 655–662.
[BibTeX]@InProceedings{Abramov:Mehler:2007:b, Author = {Abramov, Olga and Mehler, Alexander}, Title = {Structural Differentiae of Text Types. A Quantitative Model}, BookTitle = {Proceedings of the 31st Annual Conference of the German Classification Society on Data Analysis, Machine Learning, and Applications (GfKl)}, Pages = {655–662}, pdf = {http://wwwhomes.uni-bielefeld.de/opustylnikov/pustylnikov/pdfs/gfkl.pdf}, website = {http://www.springerprofessional.de/077---structural-differentiae-of-text-types--a-quantitative-model/1957362.html}, year = 2007 }
-
A. Mehler and R. Köhler, Aspects of Automatic Text Analysis: Festschrift in Honor of Burghard Rieger, A. Mehler and R. Köhler, Eds., Berlin/New York: Springer, 2007.
[BibTeX]@Book{Mehler:Koehler:2007:a, Author = {Mehler, Alexander and Köhler, Reinhard}, Editor = {Mehler, Alexander and Köhler, Reinhard}, Title = {Aspects of Automatic Text Analysis: Festschrift in Honor of Burghard Rieger}, Publisher = {Springer}, Series = {Studies in Fuzziness and Soft Computing}, Address = {Berlin/New York}, image = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/AspectsOfAutomaticTextAnalysis.jpg}, pagetotal = {464}, review = {http://www.degruyter.com/view/j/zrs.2011.3.issue-2/zrs.2011.050/zrs.2011.050.xml}, review2 = {http://irsg.bcs.org/informer/Informer27.pdf}, website = {http://www.springer.com/de/book/9783540375203}, year = 2007 }
-
A. Mehler and A. Storrer, "What are Ontologies Good For? Evaluating Terminological Ontologies in the Framework of Text Graph Classification," in Proceedings of OTT '06 – Ontologies in Text Technology: Approaches to Extract Semantic Knowledge from Structured Information, Osnabrück, 2007, pp. 11-18.
[BibTeX]@InProceedings{Mehler:Storrer:2007, Author = {Mehler, Alexander and Storrer, Angelika}, Title = {What are Ontologies Good For? Evaluating Terminological Ontologies in the Framework of Text Graph Classification}, BookTitle = {Proceedings of OTT '06 – Ontologies in Text Technology: Approaches to Extract Semantic Knowledge from Structured Information}, Editor = {Mönnich, Uwe and Kühnberger, Kai-Uwe}, Series = {Publications of the Institute of Cognitive Science (PICS)}, Pages = {11-18}, Address = {Osnabrück}, pdf = {http://cogsci.uni-osnabrueck.de/~ott06/ott06-abstracts/Mehler_Storrer_abstract.pdf}, website = {http://citeseer.uark.edu:8080/citeseerx/viewdoc/summary?doi=10.1.1.91.2979}, year = 2007 }
-
M. Stührenberg, D. Goecke, N. Diewald, A. Mehler, and I. Cramer, "Web-based Annotation of Anaphoric Relations and Lexical Chains," in Proceedings of the Linguistic Annotation Workshop, ACL 2007, 2007, p. 140–147.
[BibTeX]@InProceedings{Stuehrenberg:Goecke:Diewald:Mehler:Cramer:2007:a, Author = {Stührenberg, Maik and Goecke, Daniela and Diewald, Nils and Mehler, Alexander and Cramer, Irene}, Title = {Web-based Annotation of Anaphoric Relations and Lexical Chains}, BookTitle = {Proceedings of the Linguistic Annotation Workshop, ACL 2007}, Pages = {140–147}, pdf = {http://www.aclweb.org/anthology/W07-1523}, website = {https://www.researchgate.net/publication/234800610_Web-based_annotation_of_anaphoric_relations_and_lexical_chains}, year = 2007 }
-
R. Ferrer i Cancho, A. Mehler, O. Abramov, and A. Díaz-Guilera, "Correlations in the organization of large-scale syntactic dependency networks," in Proceedings of Graph-based Methods for Natural Language Processing (TextGraphs-2) at the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2007), Rochester, New York, 2007, pp. 65-72.
[BibTeX]@InProceedings{Ferrer:i:Cancho:Mehler:Pustylnikov:Diaz-Guilera:2007:a, Author = {Ferrer i Cancho, Ramon and Mehler, Alexander and Abramov, Olga and Díaz-Guilera, Albert}, Title = {Correlations in the organization of large-scale syntactic dependency networks}, BookTitle = {Proceedings of Graph-based Methods for Natural Language Processing (TextGraphs-2) at the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2007), Rochester, New York}, Pages = {65-72}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/ferrer-i-cancho_mehler_pustylnikov_diaz-guilera_2007_a.pdf}, year = 2007 }
-
R. Gleim, A. Mehler, H. Eikmeyer, and H. Rieser, "Ein Ansatz zur Repräsentation und Verarbeitung großer Korpora multimodaler Daten," in Data Structures for Linguistic Resources and Applications. Proceedings of the Biennial GLDV Conference 2007, 11.–13. April, Universität Tübingen, Tübingen, 2007, pp. 275-284.
[BibTeX]@InProceedings{Gleim:Mehler:Eikmeyer:Rieser:2007, Author = {Gleim, Rüdiger and Mehler, Alexander and Eikmeyer, Hans-Jürgen and Rieser, Hannes}, Title = {Ein Ansatz zur Repr{\"a}sentation und Verarbeitung gro{\ss}er Korpora multimodaler Daten}, BookTitle = {Data Structures for Linguistic Resources and Applications. Proceedings of the Biennial GLDV Conference 2007, 11.–13. April, Universit{\"a}t Tübingen}, Editor = {Rehm, Georg and Witt, Andreas and Lemnitzer, Lothar}, Pages = {275-284}, Address = {Tübingen}, Publisher = {Narr}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/gleim_mehler_eikmeyer_rieser_2007.pdf}, year = 2007 }
-
A. Mehler, "Aspectos Metodológicos da Semiótica Computacional," in Computação, Cognição e Semiose, J. Queiroz, R. Gudwin, and A. Loula, Eds., Federal University of Bahia: EDUFBA, 2007, pp. 145-157.
[BibTeX]@InCollection{Mehler:2004:2007, Author = {Mehler, Alexander}, Title = {Aspectos Metodológicos da Semiótica Computacional}, BookTitle = {Computação, Cognição e Semiose}, Publisher = {EDUFBA}, Editor = {Queiroz, João and Gudwin, Ricardo and Loula, Angelo}, Pages = {145-157}, Address = {Federal University of Bahia}, year = 2007 }
-
A. Mehler, "Compositionality in Quantitative Semantics. A Theoretical Perspective on Text Mining," in Aspects of Automatic Text Analysis, A. Mehler and R. Köhler, Eds., Berlin/New York: Springer, 2007, pp. 139-167.
[Abstract] [BibTeX]This chapter introduces a variant of the principle of compositionality in quantitative text semantics as an alternative to the bag-of-features approach. The variant includes effects of context-sensitive interpretation as well as processes of meaning constitution and change in the sense of usage-based semantics. Its starting point is a combination of semantic space modeling and text structure analysis. The principle is implemented by means of a hierarchical constraint satisfaction process which utilizes the notion of hierarchical text structure superimposed by graph-inducing coherence relations. The major contribution of the chapter is a conceptualization and formalization of the principle of compositionality in terms of semantic spaces which tackles some well known deficits of existing approaches. In particular this relates to the missing linguistic interpretability of statistical meaning representations.
@InCollection{Mehler:2007:b, Author = {Mehler, Alexander}, Title = {Compositionality in Quantitative Semantics. A Theoretical Perspective on Text Mining}, BookTitle = {Aspects of Automatic Text Analysis}, Publisher = {Springer}, Editor = {Mehler, Alexander and Köhler, Reinhard}, Series = {Studies in Fuzziness and Soft Computing}, Pages = {139-167}, Address = {Berlin/New York}, abstract = {This chapter introduces a variant of the principle of compositionality in quantitative text semantics as an alternative to the bag-of-features approach. The variant includes effects of context-sensitive interpretation as well as processes of meaning constitution and change in the sense of usage-based semantics. Its starting point is a combination of semantic space modeling and text structure analysis. The principle is implemented by means of a hierarchical constraint satisfaction process which utilizes the notion of hierarchical text structure superimposed by graph-inducing coherence relations. The major contribution of the chapter is a conceptualization and formalization of the principle of compositionality in terms of semantic spaces which tackles some well known deficits of existing approaches. In particular this relates to the missing linguistic interpretability of statistical meaning representations. }, website = {http://www.springerlink.com/content/x214w527g42x0116/}, year = 2007 }
-
M. Dehmer and A. Mehler, "A New Method of Measuring the Similarity for a Special Class of Directed Graphs," Tatra Mountains Mathematical Publications, vol. 36, pp. 39-59, 2007.
[BibTeX]@Article{Dehmer:Mehler:2007:a, Author = {Dehmer, Matthias and Mehler, Alexander}, Title = {A New Method of Measuring the Similarity for a Special Class of Directed Graphs}, Journal = {Tatra Mountains Mathematical Publications}, Volume = {36}, Pages = {39-59}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/dehmer_mehler_2004_a.pdf}, website = {https://www.researchgate.net/publication/228905939_A_new_method_of_measuring_similarity_for_a_special_class_of_directed_graphs}, year = 2007 }
-
P. Geibel, U. Krumnack, O. Abramov, A. Mehler, H. Gust, and K. Kühnberger, "Structure-Sensitive Learning of Text Types," in Proceedings of AI 2007: Advances in Artificial Intelligence, 20th Australian Joint Conference on Artificial Intelligence, Gold Coast, Australia, December 2-6, 2007, 2007, pp. 642-646.
[Abstract] [BibTeX]In this paper, we discuss the structure based classification of documents based on their logical document structure, i.e., their DOM trees. We describe a method using predefined structural features and also four tree kernels suitable for such structures. We evaluate the methods experimentally on a corpus containing the DOM trees of newspaper articles, and on the well-known SUSANNE corpus. We will demonstrate that, for the two corpora, many text types can be learned based on structural features only.
@InProceedings{Geibel:Krumnack:Pustylnikov:Mehler:Gust:Kuehnberger:2007, Author = {Geibel, Peter and Krumnack, Ulf and Abramov, Olga and Mehler, Alexander and Gust, Helmar and Kühnberger, Kai-Uwe}, Title = {Structure-Sensitive Learning of Text Types}, BookTitle = {Proceedings of AI 2007: Advances in Artificial Intelligence, 20th Australian Joint Conference on Artificial Intelligence, Gold Coast, Australia, December 2-6, 2007}, Editor = {Orgun, Mehmet A. and Thornton, John}, Volume = {4830}, Series = {Lecture Notes in Computer Science}, Pages = {642-646}, Publisher = {Springer}, abstract = {In this paper, we discuss the structure based classification of documents based on their logical document structure, i.e., their DOM trees. We describe a method using predefined structural features and also four tree kernels suitable for such structures. We evaluate the methods experimentally on a corpus containing the DOM trees of newspaper articles, and on the well-known SUSANNE corpus. We will demonstrate that, for the two corpora, many text types can be learned based on structural features only.}, website = {http://www.springerlink.com/content/w574377ww1h6m212/}, year = 2007 }
2006 (22)
-
A. Mehler, R. Gleim, and M. Dehmer, "Towards Structure-Sensitive Hypertext Categorization," in Proceedings of the 29th Annual Conference of the German Classification Society, March 9-11, 2005, Universität Magdeburg, Berlin/New York, 2006, pp. 406-413.
[Abstract] [BibTeX]Hypertext categorization is the task of automatically assigning category labels to hypertext units. Comparable to text categorization it stays in the area of function learning based on the bag-of-features approach. This scenario faces the problem of a many-to-many relation between websites and their hidden logical document structure. The paper argues that this relation is a prevalent characteristic which interferes any effort of applying the classical apparatus of categorization to web genres. This is confirmed by a threefold experiment in hypertext categorization. In order to outline a solution to this problem, the paper sketches an alternative method of unsupervised learning which aims at bridging the gap between statistical and structural pattern recognition (Bunke et al. 2001) in the area of web mining.
@InProceedings{Mehler:Gleim:Dehmer:2006, Author = {Mehler, Alexander and Gleim, Rüdiger and Dehmer, Matthias}, Title = {Towards Structure-Sensitive Hypertext Categorization}, BookTitle = {Proceedings of the 29th Annual Conference of the German Classification Society, March 9-11, 2005, Universit{\"a}t Magdeburg}, Editor = {Spiliopoulou, Myra and Kruse, Rudolf and Borgelt, Christian and Nürnberger, Andreas and Gaul, Wolfgang}, Pages = {406-413}, Address = {Berlin/New York}, Publisher = {Springer}, abstract = {Hypertext categorization is the task of automatically assigning category labels to hypertext units. Comparable to text categorization it stays in the area of function learning based on the bag-of-features approach. This scenario faces the problem of a many-to-many relation between websites and their hidden logical document structure. The paper argues that this relation is a prevalent characteristic which interferes any effort of applying the classical apparatus of categorization to web genres. This is confirmed by a threefold experiment in hypertext categorization. In order to outline a solution to this problem, the paper sketches an alternative method of unsupervised learning which aims at bridging the gap between statistical and structural pattern recognition (Bunke et al. 2001) in the area of web mining.}, website = {http://www.springerlink.com/content/l7665tm3u241317l/}, year = 2006 }
-
A. Mehler, "A Network Perspective on Intertextuality," in Exact Methods in the Study of Language and Text, P. Grzybek and R. Köhler, Eds., Berlin/New York: De Gruyter, 2006, pp. 437-446.
[BibTeX]@InCollection{Mehler:2006:d, Author = {Mehler, Alexander}, Title = {A Network Perspective on Intertextuality}, BookTitle = {Exact Methods in the Study of Language and Text}, Publisher = {De Gruyter}, Editor = {Grzybek, Peter and Köhler, Reinhard}, Series = {Quantitative Linguistics}, Pages = {437-446}, Address = {Berlin/New York}, year = 2006 }
-
M. Dehmer, F. Emmert-Streib, A. Mehler, and J. Kilian, "Measuring the Structural Similarity of Web-based Documents: A Novel Approach," International Journal of Computational Intelligence, vol. 3, iss. 1, pp. 1-7, 2006.
[Abstract] [BibTeX]Most known methods for measuring the structural similarity of document structures are based on, e.g., tag measures, path metrics and tree measures in terms of their DOM-Trees. Other methods measures the similarity in the framework of the well known vector space model. In contrast to these we present a new approach to measuring the structural similarity of web-based documents represented by so called generalized trees which are more general than DOM-Trees which represent only directed rooted trees. We will design a new similarity measure for graphs representing web-based hypertext structures. Our similarity measure is mainly based on a novel representation of a graph as strings of linear integers, whose components represent structural properties of the graph. The similarity of two graphs is then defined as the optimal alignment of the underlying property strings. In this paper we apply the well known technique of sequence alignments to solve a novel and challenging problem: Measuring the structural similarity of generalized trees. More precisely, we first transform our graphs considered as high dimensional objects in linear structures. Then we derive similarity values from the alignments of the property strings in order to measure the structural similarity of generalized trees. Hence, we transform a graph similarity problem to a string similarity problem. We demonstrate that our similarity measure captures important structural information by applying it to two different test sets consisting of graphs representing web-based documents.
@Article{Dehmer:Emmert:Streib:Mehler:Kilian:2006, Author = {Dehmer, Matthias and Emmert-Streib, Frank and Mehler, Alexander and Kilian, Jürgen}, Title = {Measuring the Structural Similarity of Web-based Documents: A Novel Approach}, Journal = {International Journal of Computational Intelligence}, Volume = {3}, Number = {1}, Pages = {1-7}, abstract = {Most known methods for measuring the structural similarity of document structures are based on, e.g., tag measures, path metrics and tree measures in terms of their DOM-Trees. Other methods measures the similarity in the framework of the well known vector space model. In contrast to these we present a new approach to measuring the structural similarity of web-based documents represented by so called generalized trees which are more general than DOM-Trees which represent only directed rooted trees. We will design a new similarity measure for graphs representing web-based hypertext structures. Our similarity measure is mainly based on a novel representation of a graph as strings of linear integers, whose components represent structural properties of the graph. The similarity of two graphs is then defined as the optimal alignment of the underlying property strings. In this paper we apply the well known technique of sequence alignments to solve a novel and challenging problem: Measuring the structural similarity of generalized trees. More precisely, we first transform our graphs considered as high dimensional objects in linear structures. Then we derive similarity values from the alignments of the property strings in order to measure the structural similarity of generalized trees. Hence, we transform a graph similarity problem to a string similarity problem. We demonstrate that our similarity measure captures important structural information by applying it to two different test sets consisting of graphs representing web-based documents.}, pdf = {http://waset.org/publications/15928/measuring-the-structural-similarity-of-web-based-documents-a-novel-approach}, website = {http://connection.ebscohost.com/c/articles/24839145/measuring-structural-similarity-web-based-documents-novel-approach}, year = 2006 }
-
A. Mehler and R. Gleim, "The Net for the Graphs – Towards Webgenre Representation for Corpus Linguistic Studies," in WaCky! Working Papers on the Web as Corpus, M. Baroni and S. Bernardini, Eds., Bologna: Gedit, 2006, pp. 191-224.
[BibTeX]@InCollection{Mehler:Gleim:2006:b, Author = {Mehler, Alexander and Gleim, Rüdiger}, Title = {The Net for the Graphs – Towards Webgenre Representation for Corpus Linguistic Studies}, BookTitle = {WaCky! Working Papers on the Web as Corpus}, Publisher = {Gedit}, Editor = {Baroni, Marco and Bernardini, Silvia}, Pages = {191-224}, Address = {Bologna}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.510.4125}, year = 2006 }
-
R. Gleim, A. Mehler, and M. Dehmer, "Web Corpus Mining by Instance of Wikipedia," in Proceedings of the EACL 2006 Workshop on Web as Corpus, April 3-7, 2006, Trento, Italy, 2006, pp. 67-74.
[Abstract] [BibTeX]Workshop organizer: Adam Kilgarriff
@InProceedings{Gleim:Mehler:Dehmer:2006:a, Author = {Gleim, Rüdiger and Mehler, Alexander and Dehmer, Matthias}, Title = {Web Corpus Mining by Instance of Wikipedia}, BookTitle = {Proceedings of the EACL 2006 Workshop on Web as Corpus, April 3-7, 2006, Trento, Italy}, Editor = {Kilgariff, Adam and Baroni, Marco}, Pages = {67-74}, abstract = {Workshop organizer: Adam Kilgarriff}, pdf = {http://www.aclweb.org/anthology/W06-1710}, website = {http://pub.uni-bielefeld.de/publication/1773538}, year = 2006 }
-
A. Mehler, "In Search of a Bridge Between Network Analysis in Computational Linguistics and Computational Biology-A Conceptual Note.," in BIOCOMP, 2006, pp. 496-502.
[BibTeX]@InProceedings{mehler:2006, Author = {Mehler, Alexander}, Title = {In Search of a Bridge Between Network Analysis in Computational Linguistics and Computational Biology-A Conceptual Note.}, BookTitle = {BIOCOMP}, Pages = {496--502}, pdf = {https://pdfs.semanticscholar.org/81aa/0b840ed413089d69908cff60628a92609ccd.pdf}, year = 2006 }
-
T. vor der Brück and S. Busemann, "Automatic Error Correction for Tree-Mapping Grammars," in Proceedings of KONVENS 2006, Konstanz, Germany, 2006, pp. 1-8.
[Abstract] [BibTeX]Tree mapping grammars are used in natural language generation (NLG) to map non-linguistic input onto a derivation tree from which the target text can be trivially read off as the terminal yield. Such grammars may consist of a large number of rules. Finding errors is quite tedious and sometimes very time-consuming. Often the generation fails because the relevant input subtree is not specified correctly. This work describes a method to detect and correct wrong assignments of input subtrees to grammar categories by cross-validating grammar rules with the given input structures. The result is implemented in a grammar development workbench and helps accelerating the grammar writer's work considerably.
@InProceedings{vor:der:Brueck:Busemann:2006, Author = {vor der Brück, Tim and Busemann, Stephan}, Title = {Automatic Error Correction for Tree-Mapping Grammars}, BookTitle = {Proceedings of KONVENS 2006}, Pages = {1--8}, Address = {Konstanz, Germany}, abstract = {Tree mapping grammars are used in natural language generation (NLG) to map non-linguistic input onto a derivation tree from which the target text can be trivially read off as the terminal yield. Such grammars may consist of a large number of rules. Finding errors is quite tedious and sometimes very time-consuming. Often the generation fails because the relevant input subtree is not specified correctly. This work describes a method to detect and correct wrong assignments of input subtrees to grammar categories by cross-validating grammar rules with the given input structures. The result is implemented in a grammar development workbench and helps accelerating the grammar writer's work considerably.}, annote = {editor: Miriam Butt}, isbn = {3-89318-050-8}, month = {October}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/brueck-busemann-konvens06.pdf}, url = {http://pi7.fernuni-hagen.de/brueck/papers/brueck-busemann-konvens06.pdf}, website = {http://www.dfki.de/lt/publication_show.php?id=3602}, year = 2006 }
-
A. Kranstedt, A. Lücking, T. Pfeiffer, H. Rieser, and M. Staudacher, "Measuring and Reconstructing Pointing in Visual Contexts," in brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue, Potsdam, 2006, pp. 82-89.
[Abstract] [BibTeX]We describe an experiment to gather original data on geometrical aspects of pointing. In particular, we are focusing upon the concept of the pointing cone, a geometrical model of a pointing’s extension. In our setting we employed methodological and technical procedures of a new type to integrate data from annotations as well as from tracker recordings. We combined exact information on position and orientation with rater’s classifications. Our first results seem to challenge classical linguistic and philosophical theories of demonstration in that they advise to separate pointings from reference.
@InProceedings{Kranstedt:et:al:2006:c, Author = {Kranstedt, Alfred and Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes and Staudacher, Marc}, Title = {Measuring and Reconstructing Pointing in Visual Contexts}, BookTitle = {brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue}, Editor = {David Schlangen and Raquel Fernández}, Pages = {82--89}, Address = {Potsdam}, Publisher = {Universit{\"a}tsverlag Potsdam}, abstract = {We describe an experiment to gather original data on geometrical aspects of pointing. In particular, we are focusing upon the concept of the pointing cone, a geometrical model of a pointing’s extension. In our setting we employed methodological and technical procedures of a new type to integrate data from annotations as well as from tracker recordings. We combined exact information on position and orientation with rater’s classifications. Our first results seem to challenge classical linguistic and philosophical theories of demonstration in that they advise to separate pointings from reference.}, keywords = {own}, month = {9}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/measure.pdf}, website = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.8472}, year = 2006 }
-
A. Lücking, H. Rieser, and M. Staudacher, "Multi-modal Integration for Gesture and Speech," in brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue, Potsdam, 2006, pp. 106-113.
[Abstract] [BibTeX]Demonstratives, in particular gestures that 'only' accompany speech, are not a big issue in current theories of grammar. If we deal with gestures, fixing their function is one big problem, the other one is how to integrate the representations originating from different channels and, ultimately, how to determine their composite meanings. The growing interest in multi-modal settings, computer simulations, human-machine interfaces and VR-applications increases the need for theories of multi-modal structures and events. In our workshop-contribution we focus on the integration of multi-modal contents and investigate different approaches dealing with this problem such as Johnston et al. (1997) and Johnston (1998), Johnston and Bangalore (2000), Chierchia (1995), Asher (2005), and Rieser (2005).
@InProceedings{Luecking:Rieser:Staudacher:2006:a, Author = {Lücking, Andy and Rieser, Hannes and Staudacher, Marc}, Title = {Multi-modal Integration for Gesture and Speech}, BookTitle = {brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue}, Editor = {David Schlangen and Raquel Fernández}, Pages = {106--113}, Address = {Potsdam}, Publisher = {Universit{\"a}tsverlag Potsdam}, abstract = {Demonstratives, in particular gestures that 'only' accompany speech, are not a big issue in current theories of grammar. If we deal with gestures, fixing their function is one big problem, the other one is how to integrate the representations originating from different channels and, ultimately, how to determine their composite meanings. The growing interest in multi-modal settings, computer simulations, human-machine interfaces and VR-applications increases the need for theories of multi-modal structures and events. In our workshop-contribution we focus on the integration of multi-modal contents and investigate different approaches dealing with this problem such as Johnston et al. (1997) and Johnston (1998), Johnston and Bangalore (2000), Chierchia (1995), Asher (2005), and Rieser (2005).}, keywords = {own}, month = {9}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mm-int-brandial-final.pdf}, year = 2006 }
-
A. Kranstedt, A. Lücking, T. Pfeiffer, H. Rieser, and I. Wachsmuth, "Deictic Object Reference in Task-oriented Dialogue," in Situated Communication, G. Rickheit and I. Wachsmuth, Eds., Berlin: De Gruyter Mouton, 2006, pp. 155-207.
[Abstract] [BibTeX]This chapter presents an original approach towards a detailed understanding of the usage of pointing gestures accompanying referring expressions. This effort is undertaken in the context of human-machine interaction integrating empirical studies, theory of grammar and logics, and simulation techniques. In particular, we take steps to classify the role of pointing in deictic expressions and to model the focussed area of pointing gestures, the so-called pointing cone. This pointing cone serves as a central concept in a formal account of multi-modal integration at the linguistic speech-gesture interface as well as in a computational model of processing multi-modal deictic expressions.
@InCollection{Kranstedt:et:al:2006:b, Author = {Kranstedt, Alfred and Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes and Wachsmuth, Ipke}, Title = {Deictic Object Reference in Task-oriented Dialogue}, BookTitle = {Situated Communication}, Publisher = {De Gruyter Mouton}, Editor = {Gert Rickheit and Ipke Wachsmuth}, Pages = {155--207}, Address = {Berlin}, abstract = {This chapter presents an original approach towards a detailed understanding of the usage of pointing gestures accompanying referring expressions. This effort is undertaken in the context of human-machine interaction integrating empirical studies, theory of grammar and logics, and simulation techniques. In particular, we take steps to classify the role of pointing in deictic expressions and to model the focussed area of pointing gestures, the so-called pointing cone. This pointing cone serves as a central concept in a formal account of multi-modal integration at the linguistic speech-gesture interface as well as in a computational model of processing multi-modal deictic expressions.}, keywords = {own}, website = {http://pub.uni-bielefeld.de/publication/1894485}, year = 2006 }
-
A. Kranstedt, A. Lücking, T. Pfeiffer, H. Rieser, and I. Wachsmuth, "Deixis: How to Determine Demonstrated Objects Using a Pointing Cone," in Gesture in Human-Computer Interaction and Simulation, S. Gibet, N. Courty, and J. Kamp, Eds., Berlin: Springer, 2006, pp. 300-311.
[Abstract] [BibTeX]We present a collaborative approach towards a detailed understanding of the usage of pointing gestures accompanying referring expressions. This effort is undertaken in the context of human-machine interaction integrating empirical studies, theory of grammar and logics, and simulation techniques. In particular, we attempt to measure the precision of the focussed area of a pointing gesture, the so-called pointing cone. The pointing cone serves as a central concept in a formal account of multi-modal integration at the linguistic speech-gesture interface as well as in a computational model of processing multi-modal deictic expressions.
@InCollection{Kranstedt:et:al:2006:a, Author = {Kranstedt, Alfred and Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes and Wachsmuth, Ipke}, Title = {Deixis: How to Determine Demonstrated Objects Using a Pointing Cone}, BookTitle = {Gesture in Human-Computer Interaction and Simulation}, Publisher = {Springer}, Editor = {Sylvie Gibet and Nicolas Courty and Jean-Francois Kamp}, Pages = {300--311}, Address = {Berlin}, abstract = {We present a collaborative approach towards a detailed understanding of the usage of pointing gestures accompanying referring expressions. This effort is undertaken in the context of human-machine interaction integrating empirical studies, theory of grammar and logics, and simulation techniques. In particular, we attempt to measure the precision of the focussed area of a pointing gesture, the so-called pointing cone. The pointing cone serves as a central concept in a formal account of multi-modal integration at the linguistic speech-gesture interface as well as in a computational model of processing multi-modal deictic expressions.}, anote = {6th International Gesture Workshop, Berder Island, France, 2005, Revised Selected Papers}, keywords = {own}, website = {http://www.springerlink.com/content/712036hp5v2q8408/}, year = 2006 }
-
T. Pfeiffer, A. Kranstedt, and A. Lücking, "Sprach-Gestik Experimente mit IADE, dem Interactive Augmented Data Explorer," in Proceedings: Dritter Workshop Virtuelle und Erweiterte Realität der GI-Fachgruppe VR/AR, Koblenz, 2006.
[Abstract] [BibTeX]Für die empirische Erforschung natürlicher menschlicher Kommunikation sind wir auf die Akquise und Auswertung umfangreicher Daten angewiesen. Die Modalitäten, über die sich Menschen ausdrücken können, sind sehr unterschiedlich - und genauso verschieden sind die Repräsentationen, mit denen sie für die Empirie verfügbar gemacht werden können. Für eine Untersuchung des Zeigeverhaltens bei der Referenzierung von Objekten haben wir mit IADE ein Framework für die Aufzeichnung, Analyse und Resimulation von Sprach-Gestik Daten entwickelt. Mit dessen Hilfe können wir für unsere Forschung entscheidende Fortschritte in der linguistischen Experimentalmethodik machen.
@InProceedings{Pfeiffer:Kranstedt:Luecking:2006, Author = {Pfeiffer, Thies and Kranstedt, Alfred and Lücking, Andy}, Title = {Sprach-Gestik Experimente mit IADE, dem Interactive Augmented Data Explorer}, BookTitle = {Proceedings: Dritter Workshop Virtuelle und Erweiterte Realit{\"a}t der GI-Fachgruppe VR/AR}, Address = {Koblenz}, abstract = {Für die empirische Erforschung natürlicher menschlicher Kommunikation sind wir auf die Akquise und Auswertung umfangreicher Daten angewiesen. Die Modalit{\"a}ten, über die sich Menschen ausdrücken können, sind sehr unterschiedlich - und genauso verschieden sind die Repr{\"a}sentationen, mit denen sie für die Empirie verfügbar gemacht werden können. Für eine Untersuchung des Zeigeverhaltens bei der Referenzierung von Objekten haben wir mit IADE ein Framework für die Aufzeichnung, Analyse und Resimulation von Sprach-Gestik Daten entwickelt. Mit dessen Hilfe können wir für unsere Forschung entscheidende Fortschritte in der linguistischen Experimentalmethodik machen.}, keywords = {own}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Pfeiffer-Kranstedt-Luecking-IADE.pdf}, website = {http://pub.uni-bielefeld.de/publication/2426853}, year = 2006 }
-
A. Lücking, H. Rieser, and M. Staudacher, "SDRT and Multi-modal Situated Communication," in brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue, 2006, pp. 72-79.
[BibTeX]@InProceedings{Luecking:Rieser:Stauchdacher:2006:b, Author = {Lücking, Andy and Rieser, Hannes and Staudacher, Marc}, Title = {SDRT and Multi-modal Situated Communication}, BookTitle = {brandial '06 -- Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue}, Editor = {David Schlangen and Raquel Fernández}, Pages = {72--79}, Publisher = {Universit{\"a}tsverlag Potsdam}, keywords = {own}, month = {9}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/sdrt-sitcomm-brandial-final.pdf}, year = 2006 }
-
M. Z. Islam and M. Khan, "JKimmo: A Multilingual Computational Morphology Framework for PC-KIMMO," in 9th International Conference on Computer and Information Technology (ICCIT 2006), Dhaka, Bangladesh, 2006.
[Abstract] [BibTeX]Morphological analysis is of fundamental interest in computational linguistics and language processing. While there are established morphological analyzers for mostly Western and a few other languages using localized interfaces, the same cannot be said for Indic and other less-studied languages for which language processing is just beginning. There are three primary obstacles to computational morphological analysis of these less-studied languages: the generative rules that define the language morphology, the morphological processor, and the computational interface that a linguist can use to experiment with the generative rules. In this paper, we present JKimmo, a multilingual morphological open-source framework that uses the PC-KIMMO two-level morphological processor and provides a localized interface for Bangla morphological analysis. We then apply Jkimmo to Bangla computational morphology, demonstrating both its recognition and generation capabilities. Jkimmo’s internationalization (i18n) frame-work allows easy localization in other languages as well, using a property file for the interface definitions and a transliteration scheme for the analysis.
@InProceedings{Zahurul:Khan:2006, Author = {Islam, Md. Zahurul and Khan, Mumit}, Title = {JKimmo: A Multilingual Computational Morphology Framework for PC-KIMMO}, BookTitle = {9th International Conference on Computer and Information Technology (ICCIT 2006), Dhaka, Bangladesh}, abstract = {Morphological analysis is of fundamental interest in computational linguistics and language processing. While there are established morphological analyzers for mostly Western and a few other languages using localized interfaces, the same cannot be said for Indic and other less-studied languages for which language processing is just beginning. There are three primary obstacles to computational morphological analysis of these less-studied languages: the generative rules that define the language morphology, the morphological processor, and the computational interface that a linguist can use to experiment with the generative rules. In this paper, we present JKimmo, a multilingual morphological open-source framework that uses the PC-KIMMO two-level morphological processor and provides a localized interface for Bangla morphological analysis. We then apply Jkimmo to Bangla computational morphology, demonstrating both its recognition and generation capabilities. Jkimmo’s internationalization (i18n) frame-work allows easy localization in other languages as well, using a property file for the interface definitions and a transliteration scheme for the analysis.}, owner = {zahurul}, pdf = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/JKimmo_-A_Multilingual_Computational_Morphology_Framework_for_PC-KIMMO.pdf}, timestamp = {2011.08.02}, website = {https://www.researchgate.net/publication/237728403_JKimmo_A_Multilingual_Computational_Morphology_Framework_for_PC-KIMMO}, year = 2006 }
-
T. Rownok, M. Z. Islam, and M. Khan, "Bangla Text Input and Rendering Support for Short Message Service on Mobile Devices," in 9th International Conference on Computer and Information Technology (ICCIT 2006), Dhaka, Bangladesh, 2006.
[Abstract] [BibTeX]Technology is the most important thing that involve in our everyday life. It is involving in almost every aspect of life like communication, work, shopping, recreation etc. Communication through mobile devices is the most effective and easy way now a day. It is faster, easier and you can communicate whenever you want from any-where. Mobile messaging or short message service is one of the popular ways to communicate using mobile devices. It is a big challenge to write and display Bangla characters on mobile devices. In this paper, we describe a Bangla text input method and rendering support on mobile devices for short message service.
@InProceedings{Rownok:Zahurul:Khan:2006, Author = {Rownok, Tofazzal and Islam, Md. Zahurul and Khan, Mumit}, Title = {Bangla Text Input and Rendering Support for Short Message Service on Mobile Devices}, BookTitle = {9th International Conference on Computer and Information Technology (ICCIT 2006), Dhaka, Bangladesh}, abstract = {Technology is the most important thing that involve in