Prof. Dr. Alexander Mehler

@inproceedings{Abrami:et:al:2024:a,
  abstract  = {In 2022, the largest German-speaking corpus of parliamentary protocols
               from three different centuries, on a national and federal level
               from the countries of Germany, Austria, Switzerland and Liechtenstein,
               was collected and published - GerParCor. Through GerParCor, it
               became possible to provide for the first time various parliamentary
               protocols which were not available digitally and, moreover, could
               not be retrieved and processed in a uniform manner. Furthermore,
               GerParCor was additionally preprocessed using NLP methods and
               made available in XMI format. In this paper, GerParCor is significantly
               updated by including all new parliamentary protocols in the corpus,
               as well as adding and preprocessing further parliamentary protocols
               previously not covered, so that a period up to 1797 is now covered.
               Besides the integration of a new, state-of-the-art and appropriate
               NLP preprocessing for the handling of large text corpora, this
               update also provides an overview of the further reuse of GerParCor
               by presenting various provisioning capabilities such as API's,
               among others.},
  address   = {Torino, Italy},
  author    = {Abrami, Giuseppe and Bagci, Mevl{\"u}t and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  pages     = {7707--7716},
  publisher = {ELRA and ICCL},
  title     = {{G}erman Parliamentary Corpus ({G}er{P}ar{C}or) Reloaded},
  url       = {https://aclanthology.org/2024.lrec-main.681},
  pdf       = {https://aclanthology.org/2024.lrec-main.681.pdf},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/GerParCor_Reloaded_Poster.pdf},
  video     = {https://www.youtube.com/watch?v=5X-w_oXOAYo},
  keywords  = {gerparcor,corpus},
  year      = {2024}
}

@inproceedings{Konca:et:al:2024,
  abstract  = {A useful semantic role-annotated resource for training semantic
               role models for the German language is missing. We point out some
               problems of previous resources and provide a new one due to a
               combined translation and alignment process: The gold standard
               CoNLL-2012 semantic role annotations are translated into German.
               Semantic role labels are transferred due to alignment models.
               The resulting dataset is used to train a German semantic role
               model. With F1-scores around 0.7, the major roles achieve competitive
               evaluation scores, but avoid limitations of previous approaches.
               The described procedure can be applied to other languages as well.},
  address   = {Torino, Italy},
  author    = {Konca, Maxim and L{\"u}cking, Andy and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  month     = {may},
  pages     = {7717--7727},
  publisher = {ELRA and ICCL},
  title     = {{G}erman {SRL}: Corpus Construction and Model Training},
  url       = {https://aclanthology.org/2024.lrec-main.682},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/LREC_2024_Poster_GERMAN_SRL.pdf},
  year      = {2024}
}

@inproceedings{Luecking:et:al:2024,
  abstract  = {Purpose: Based on the examples of English and German, we investigate
               to what extent parsers trained on modern variants of these languages
               can be transferred to older language levels without loss. Methods:
               We developed a treebank called DoTT (https://github.com/texttechnologylab/DoTT)
               which covers, roughly, the time period from 1800 until today,
               in conjunction with the further development of the annotation
               tool DependencyAnnotator. DoTT consists of a collection of diachronic
               corpora enriched with dependency annotations using 3 parsers,
               6 pre-trained language models, 5 newly trained models for German,
               and two tag sets (TIGER and Universal Dependencies). To assess
               how the different parsers perform on texts from different time
               periods, we created a gold standard sample as a benchmark. Results:
               We found that the parsers/models perform quite well on modern
               texts (document-level LAS ranging from 82.89 to 88.54) and slightly
               worse on older texts, as expected (average document-level LAS
               84.60 vs. 86.14), but not significantly. For German texts, the
               (German) TIGER scheme achieved slightly better results than UD.
               Conclusion: Overall, this result speaks for the transferability
               of parsers to past language levels, at least dating back until
               around 1800. This very transferability, it is however argued,
               means that studies of language change in the field of dependency
               syntax can draw on dependency distance but miss out on some grammatical
               phenomena.},
  address   = {Torino, Italy},
  author    = {L{\"u}cking, Andy and Abrami, Giuseppe and Hammerla, Leon and Rahn, Marc
               and Baumartz, Daniel and Eger, Steffen and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  month     = {may},
  pages     = {4641--4653},
  publisher = {ELRA and ICCL},
  title     = {Dependencies over Times and Tools ({D}o{TT})},
  url       = {https://aclanthology.org/2024.lrec-main.415},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/LREC_2024_Poster_DoTT.pdf},
  year      = {2024}
}

@inproceedings{Abrami:Mehler:2024,
  author    = {Abrami, Giuseppe and Mehler, Alexander},
  title     = {Efficient, uniform and scalable parallel NLP pre-processing with
               DUUI: Perspectives and Best Practice for the Digital Humanities},
  year      = {2024},
  month     = {08},
  editor    = {Karajgikar, Jajwalya and Janco, Andrew and Otis, Jessica},
  booktitle = {Digital Humanities Conference 2024 - Book of Abstracts (DH 2024)},
  location  = {Washington, DC, USA},
  series    = {DH},
  keywords  = {duui},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.13761079},
  url       = {https://doi.org/10.5281/zenodo.13761079}
  pages 	= {15--18},
  numpages  = {4}
}

@inproceedings{Henlein:et:al:2024-vicom,
  title     = {An Outlook for AI Innovation in Multimodal Communication Research},
  author    = {Henlein, Alexander and Bauer, Anastasia and Bhattacharjee, Reetu
               and Ćwiek, Aleksandra and Gregori, Alina and Kügler, Frank and Lemanski, Jens
               and Lücking, Andy and Mehler, Alexander and Prieto, Pilar and Sánchez-Ramón, Paula G.
               and Schepens, Job and Schulte-Rüther, Martin and Schweinberger, Stefan R.
               and von Eiff, Celina I.},
  keywords  = {own,conference},
  author+an = {8=highlight},
  editor    = {Duffy, Vincent G.},
  year      = {2024},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management.},
  series    = {HCII 2024. Lecture Notes in Computer Science},
  publisher = {Springer},
  address   = {Cham},
  pubstate  = {inpress},
  note      = {Forthcoming}
}

@article{Mattern:et:al:2024-vsd,
  author    = {Mattern, Dominik and Hemati, Wahed and Lücking, Andy and Mehler, Alexander},
  author+an = {3=highlight},
  keywords  = {own,article},
  title     = {On German verb sense disambiguation: {A} three-part approach based
               on linking a sense inventory ({GermaNet}) to a corpus through
               annotation ({TGVCorp}) and its use for training a {VSD} classifier
               ({TTvSense})},
  year      = {2024},
  journal   = {Journal of Language Modelling},
  pubstate  = {forthcoming},
  note      = {Forthcoming}
}

@inproceedings{Abrami:et:al:2024:b,
  author    = {Abrami, Giuseppe and Wontke, Dominik Alexander and Singh, Gurpreet
               and Mehler, Alexander},
  title     = {Va.Si.Li-ES: VR-based Dynamic Event Processing, Environment Change
               and User Feedback in Va.Si.Li-Lab},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3675154},
  doi       = {10.1145/3648188.3675154},
  abstract  = {Flexibility, adaptability, modularity, and extensibility in the
               context of a collaborative system are critical features for multi-user
               hypertext systems. In addition to facilitating acceptance and
               increasing reusability, these features simplify development cycles
               and enable a larger range of application areas. However, especially
               in virtual 3D hypertext systems, many of the features are only
               partially available or not available at all. To fill this gap,
               we present an approach to virtual hypertext systems for the realization
               of dynamic event systems. Such an event system can be created
               and serialized simultaneously at run time regarding the modification
               of situational, environmental parameters. This includes informing
               users and allowing them to participate in the environmental dynamics
               of the system. We present Va.Si.Li-ES as a module of Va.Si.Li-Lab,
               describe several environmental scenarios that can be adapted,
               and provide use cases in the context of 3D hypertext systems.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {357–-368},
  numpages  = {12},
  keywords  = {Collaborative Simulation, Environmental Event System, Hypertext, Ubiq, Va.Si.Li-Lab, Virtual Reality},
  location  = {Poznan, Poland},
  series    = {HT '24}
}

@inproceedings{Baumartz:et:al:2024,
  author    = {Baumartz, Daniel and Konca, Maxim and Mehler, Alexander and Schrottenbacher, Patrick
               and Braunheim, Dominik},
  title     = {Measuring Group Creativity of Dialogic Interaction Systems by
               Means of Remote Entailment Analysis},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3675140},
  doi       = {10.1145/3648188.3675140},
  abstract  = {We present a procedure for assessing group creativity that allows
               us to compare the contributions of human interlocutors and chatbots
               based on generative AI such as ChatGPT. We focus on everyday creativity
               in terms of dialogic communication and test four hypotheses about
               the difference between human and artificial communication. Our
               procedure is based on a test that requires interlocutors to cooperatively
               interpret a sequence of sentences for which we control for coherence
               gaps with reference to the notion of entailment. Using NLP methods,
               we automatically evaluate the spoken or written contributions
               of interlocutors (human or otherwise). The paper develops a routine
               for automatic transcription based on Whisper, for sampling texts
               based on their entailment relations, for analyzing dialogic contributions
               along their semantic embeddings, and for classifying interlocutors
               and interaction systems based on them. In this way, we highlight
               differences between human and artificial conversations under conditions
               that approximate free dialogic communication. We show that despite
               their obvious classificatory differences, it is difficult to see
               clear differences even in the domain of dialogic communication
               given the current instruments of NLP.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {153–-166},
  numpages  = {14},
  keywords  = {Creative AI, Creativity, Generative AI, Hermeneutics, NLP},
  location  = {Poznan, Poland},
  series    = {HT '24}
}

@inproceedings{Boenisch:et:al:2024,
  author    = {B\"{o}nisch, Kevin and Stoeckel, Manuel and Mehler, Alexander},
  title     = {HyperCausal: Visualizing Causal Inference in 3D Hypertext},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3677049},
  doi       = {10.1145/3648188.3677049},
  abstract  = {We present HyperCausal, a 3D hypertext visualization framework
               for exploring causal inference in generative Large Language Models
               (LLMs). HyperCausal maps the generative processes of LLMs into
               spatial hypertexts, where tokens are represented as nodes connected
               by probability-weighted edges. The edges are weighted by the prediction
               scores of next tokens, depending on the underlying language model.
               HyperCausal facilitates navigation through the causal space of
               the underlying LLM, allowing users to explore predicted word sequences
               and their branching. Through comparative analysis of LLM parameters
               such as token probabilities and search algorithms, HyperCausal
               provides insight into model behavior and performance. Implemented
               using the Hugging Face transformers library and Three.js, HyperCausal
               ensures cross-platform accessibility to advance research in natural
               language processing using concepts from hypertext research. We
               demonstrate several use cases of HyperCausal and highlight the
               potential for detecting hallucinations generated by LLMs using
               this framework. The connection with hypertext research arises
               from the fact that HyperCausal relies on user interaction to unfold
               graphs with hierarchically appearing branching alternatives in
               3D space. This approach refers to spatial hypertexts and early
               concepts of hierarchical hypertext structures. A third connection
               concerns hypertext fiction, since the branching alternatives mediated
               by HyperCausal manifest non-linearly organized reading threads
               along artificially generated texts that the user decides to follow
               optionally depending on the reading context.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {330–-336},
  numpages  = {7},
  keywords  = {3D hypertext, large language models, visualization},
  location  = {Poznan, Poland},
  series    = {HT '24},
  video     = {https://www.youtube.com/watch?v=ANHFTupnKhI}
}

@article{Boenisch:et:al:2024:b,
  author    = {B\"{o}nisch, Kevin and Mehler, Alexander and Babbili, Shaduan
               and Heinrich, Yannick and Stephan, Philipp and Abrami, Giuseppe},
  abstract  = {We present Viki LibraRy, a dynamically built library in virtual
               reality (VR) designed to visualize hypertext systems, with an
               emphasis on collaborative interaction and spatial immersion. Viki
               LibraRy goes beyond traditional methods of text distribution by
               providing a platform where users can share, process, and engage
               with textual information. It operates at the interface of VR,
               collaborative learning and spatial data processing to make reading
               tangible and memorable in a spatially mediated way. The article
               describes the building blocks of Viki LibraRy, its underlying
               architecture, and several use cases. It evaluates Viki LibraRy
               in comparison to a conventional web interface for text retrieval
               and reading. The article shows that Viki LibraRy provides users
               with spatial references for structuring their recall, so that
               they can better remember consulted texts and their meta-information
               (e.g. in terms of subject areas and content categories)},
  title     = {{Viki LibraRy: Collaborative Hypertext Browsing and Navigation
               in Virtual Reality}},
  year      = {2024},
  journal   = {New Review of Hypermedia and Multimedia},
  numpages  = {29},
  publisher = {Taylor \& Francis},
  note      = {accepted}
}

@article{Schrottenbacher:et:al:2024,
  author    = {Schrottenbacher, Patrick and Mehler, Alexander and Berg, Theresa
               and Hustedt, Jasper and Gagel, Julian and Lüttig, Timo and Abrami, Giuseppe},
  title     = {Geo-spatial hypertext in virtual reality: mapping and navigating
               global news event spaces},
  journal   = {New Review of Hypermedia and Multimedia},
  volume    = {0},
  number    = {0},
  pages     = {1--30},
  year      = {2024},
  publisher = {Taylor \& Francis},
  doi       = {10.1080/13614568.2024.2383601},
  url       = {https://doi.org/10.1080/13614568.2024.2383601},
  eprint    = {https://doi.org/10.1080/13614568.2024.2383601},
  abstract  = {Every day, a myriad of events take place that are documented and
               shared online through news articles from a variety of sources.
               As a result, as users navigate the Web, the volume of data can
               lead to information overload, making it difficult to find specific
               details about an event. We present News in Time and Space (NiTS)
               to address this issue: NiTS is a fully immersive system integrated
               into Va.Si.Li-Lab that organises textual information in a geospatial
               hypertext system in virtual reality. With NiTS, users can visualise,
               filter and interact with information currently based on GDELT
               on a virtual globe providing document networks to analyse global
               events and trends. The article describes NiTS, its event semantics
               and architecture. It evaluates NiTS in comparison to a classic
               search engine website, extended by NiTSs information filtering
               capabilities to make it comparable. Our comparison with this website
               technology, which is directly linked to the user's usage habits,
               shows that NiTS enables comparable information exploration even
               if the users have little or no experience with VR. That is, we
               observe an equivalent search result behaviour, but with the advantage
               that VR allows users to get their results with a higher level
               of usability without distracting them from their tasks. Through
               its integration with Va.Si.Li-Lab, a simulation-based learning
               environment, NiTS can be used in simulations of learning processes
               aimed at studying critical online reasoning, where Va.Si.Li-Lab
               guarantees that this can be done in relation to individual or
               groups of learners.}
}

@inproceedings{Boenisch:Mehler:2024,
  title     = {Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval
               via Bagging and SVR Ensembles},
  author    = {B\"{o}nisch, Kevin and Mehler, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 2nd Legal Information Retrieval meets Artificial
               Intelligence Workshop LIRAI 2024},
  location  = {Poznan, Poland},
  publisher = {CEUR-WS.org},
  address   = {Aachen, Germany},
  series    = {CEUR Workshop Proceedings},
  note      = {accepted},
  abstract  = {We introduce a retrieval approach leveraging Support Vector Regression
               (SVR) ensembles, bootstrap aggregation (bagging), and embedding
               spaces on the German Dataset for Legal Information Retrieval (GerDaLIR).
               By conceptualizing the retrieval task in terms of multiple binary
               needle-in-a-haystack subtasks, we show improved recall over the
               baselines (0.849 > 0.803 | 0.829) using our voting ensemble, suggesting
               promising initial results, without training or fine-tuning any
               deep learning models. Our approach holds potential for further
               enhancement, particularly through refining the encoding models
               and optimizing hyperparameters.},
  keywords  = {legal information retrieval, support vector regression, word embeddings, bagging ensemble}
}

@article{Mattern:Hemati:Lücking:Mehler:2024,
  author    = {Mattern, Dominik and Hemati, Wahed and Lücking, Andy and Mehler, Alexander},
  title     = {On German verb sense disambiguation: A three-part approach based
               on linking a sense inventory (GermaNet) to a corpus through annotation
               (TGVCorp) and using the corpus to train a VSD classifier (TTvSense)},
  abstractnote = {We develop a three-part approach to Verb Sense Disambiguation (VSD) in German. After considering a set of lexical resources and corpora, we arrive at a statistically motivated selection of a subset of verbs and their senses from GermaNet. This sub-inventory is then used to disambiguate the occurrences of the corresponding verbs in a corpus resulting from the union of TüBa-D/Z, Salsa, and E-VALBU. The corpus annotated in this way is called TGVCorp. It is used in the third part of the paper for training a classifier for VSD and for its comparative evaluation with a state-of-the-art approach in this research area, namely EWISER. Our simple classifier outperforms the transformer-based approach on the same data in both accuracy and speed in German but not in English and we discuss possible reasons.},
  journal   = {Journal of Language Modelling},
  volume    = {12},
  number    = {1},
  year      = {2024},
  month     = {Sep.},
  pages     = {155–212},
  url       = {https://jlm.ipipan.waw.pl/index.php/JLM/article/view/356}
}

@inproceedings{Luecking:Mehler:Henlein:2024-classifier,
  title     = {The Linguistic Interpretation of Non-emblematic Gestures Must
               be agreed in Dialogue: Combining Perceptual Classifiers and Grounding/Clarification
               Mechanisms},
  author    = {Lücking, Andy and Mehler, Alexander and Henlein, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue},
  series    = {SemDial'24 -- TrentoLogue},
  location  = {Università di Trento, Palazzo Piomarta, Rovereto}
}

@inproceedings{Mehler:et:al:2023:a,
  abstract  = {Simulation-based learning is a method in which learners learn
               to master real-life scenarios and tasks from simulated application
               contexts. It is particularly suitable for the use of VR technologies,
               as these allow immersive experiences of the targeted scenarios.
               VR methods are also relevant for studies on online learning, especially
               in groups, as they provide access to a variety of multimodal learning
               and interaction data. However, VR leads to a trade-off between
               technological conditions of the observability of such data and
               the openness of learner behavior. We present Va.Si.Li-Lab, a VR-L
               ab for Simulation-based Learn ing developed to address this trade-off.
               Va.Si.Li-Lab uses a graph-theoretical model based on hypergraphs
               to represent the data diversity of multimodal learning and interaction.
               We develop this data model in relation to mono- and multimodal,
               intra- and interpersonal data and interleave it with ISO-Space
               to describe distributed multiple documents from the perspective
               of their interactive generation. The paper adds three use cases
               to motivate the broad applicability of Va.Si.Li-Lab and its data
               model.},
  address   = {Cham},
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Henlein, Alexander
               and Abrami, Giuseppe and Spiekermann, Christian and Schrottenbacher, Patrick
               and Konca, Maxim and L{\"u}cking, Andy and Engel, Juliane and Quintino, Marc
               and Schreiber, Jakob and Saukel, Kevin and Zlatkin-Troitschanskaia, Olga},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management},
  editor    = {Duffy, Vincent G.},
  isbn      = {978-3-031-35741-1},
  pages     = {539--565},
  publisher = {Springer Nature Switzerland},
  title     = {A Multimodal Data Model for Simulation-Based Learning with Va.Si.Li-Lab},
  year      = {2023},
  doi       = {10.1007/978-3-031-35741-1_39}
}

@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},
  editor    = {Duffy, Vincent G.},
  title     = {Semantic Scene Builder: Towards a Context Sensitive Text-to-3D Scene Framework},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management},
  year      = {2023},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {461--479},
  abstract  = {We introduce Semantic Scene Builder (SeSB), a VR-based text-to-3D
               scene framework using SemAF (Semantic Annotation Framework) as
               a scheme for annotating discourse structures. SeSB integrates
               a variety of tools and resources by using SemAF and UIMA as a
               unified data structure to generate 3D scenes from textual descriptions.
               Based on VR, SeSB allows its users to change annotations through
               body movements instead of symbolic manipulations: from annotations
               in texts to corrections in editing steps to adjustments in generated
               scenes, all this is done by grabbing and moving objects. We evaluate
               SeSB in comparison with a state-of-the-art open source text-to-scene
               method (the only one which is publicly available) and find that
               our approach not only performs better, but also allows for modeling
               a greater variety of scenes.},
  isbn      = {978-3-031-35748-0},
  doi       = {10.1007/978-3-031-35748-0_32}
}

@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}
}

@inproceedings{Abrami:et:al:2023,
  author    = {Abrami, Giuseppe and Mehler, Alexander and Bagci, Mevl\"{u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Spiekermann, Christian and Engel, Juliane
               and Schreiber, Jakob},
  title     = {Va.Si.Li-Lab as a Collaborative Multi-User Annotation Tool in
               Virtual Reality and Its Potential Fields of Application},
  year      = {2023},
  isbn      = {9798400702327},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3603163.3609076},
  doi       = {10.1145/3603163.3609076},
  abstract  = {During the last thirty years a variety of hypertext approaches
               and virtual environments -- some virtual hypertext environments
               -- have been developed and discussed. Although the development
               of virtual and augmented reality technologies is rapid and improving,
               and many technologies can be used at affordable conditions, their
               usability for hypertext systems has not yet been explored. At
               the same time, even for virtual three-dimensional virtual and
               augmented environments, there is no generally accepted concept
               that is similar or nearly as elegant as hypertext. This gap will
               have to be filled in the next years and a good concept should
               be developed; in this article we aim to contribute in this direction
               and also introduce a prototype for a possible implementation of
               criteria for virtual hypertext simulations.},
  booktitle = {Proceedings of the 34th ACM Conference on Hypertext and Social Media},
  articleno = {22},
  numpages  = {9},
  keywords  = {VaSiLiLab, virtual hypertext, virtual reality, virtual reality simulation, authoring system},
  location  = {Rome, Italy},
  series    = {HT '23},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3603163.3609076}
}

@inproceedings{Gagel:et:al:2023,
  author    = {Gagel, Julian and Hustedt, Jasper and L\"{u}ttig, Timo and Berg, Theresa
               and Abrami, Giuseppe and Mehler, Alexander},
  title     = {News in Time and Space: Global Event Exploration in Virtual Reality},
  year      = {2023},
  isbn      = {9798400702327},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3603163.3609080},
  doi       = {10.1145/3603163.3609080},
  abstract  = {We present News in Time and Space (NiTS), a virtual reality application
               for visualization, filtering and interaction with geo-referenced
               events based on GDELT. It can be used both via VR glasses and
               as a desktop solution for shared use by multiple users with Ubiq.
               The aim of NiTS is to provide overviews of global events and trends
               in order to create a resource for their monitoring and analysis.},
  booktitle = {Proceedings of the 34th ACM Conference on Hypertext and Social Media},
  articleno = {7},
  numpages  = {3},
  keywords  = {virtual hypertext, human data interaction, spatial computing, virtual reality simulation, geographic information systems, virtual reality},
  location  = {Rome, Italy},
  series    = {HT '23},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3603163.3609080}
}

@inproceedings{Babbili:et:al:2023,
  author    = {Babbili, Shaduan and B\"{o}nisch, Kevin and Heinrich, Yannick
               and Stephan, Philipp and Abrami, Giuseppe and Mehler, Alexander},
  title     = {Viki LibraRy: A Virtual Reality Library for Collaborative Browsing
               and Navigation through Hypertext},
  year      = {2023},
  isbn      = {9798400702327},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3603163.3609079},
  doi       = {10.1145/3603163.3609079},
  abstract  = {We present Viki LibraRy, a virtual-reality-based system for generating
               and exploring online information as a spatial hypertext. It creates
               a virtual library based on Wikipedia in which Rooms are used to
               make data available via a RESTful backend. In these Rooms, users
               can browse through all articles of the corresponding Wikipedia
               category in the form of Books. In addition, users can access different
               Rooms, through virtual portals. Beyond that, the explorations
               can be done alone or collaboratively, using Ubiq.},
  booktitle = {Proceedings of the 34th ACM Conference on Hypertext and Social Media},
  articleno = {6},
  numpages  = {3},
  keywords  = {virtual reality simulation, virtual reality, virtual hypertext, virtual museum},
  location  = {Rome, Italy},
  series    = {HT '23},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3603163.3609079}
}

@inproceedings{Henlein:et:al:2023c,
  title     = {Towards grounding multimodal semantics in interaction data with Va.Si.Li-Lab},
  author    = {Henlein, Alexander and Lücking, Andy and Bagci, Mevlüt and Mehler, Alexander},
  booktitle = {Proceedings of the 8th Conference on Gesture and Speech in Interaction (GESPIN)},
  location  = {Nijmegen, Netherlands},
  year      = {2023},
  keywords  = {vasililab},
  pdf       = {https://www.gespin2023.nl/documents/talks_and_posters/GeSpIn_2023_papers/GeSpIn_2023_paper_1692.pdf}
}

@inproceedings{Leonhardt:et:al:2023,
  title     = {Unlocking the Heterogeneous Landscape of Big Data {NLP} with {DUUI}},
  author    = {Leonhardt, Alexander and Abrami, Giuseppe and Baumartz, Daniel
               and Mehler, Alexander},
  editor    = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
  year      = {2023},
  address   = {Singapore},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2023.findings-emnlp.29},
  pages     = {385--399},
  pdf       = {https://aclanthology.org/2023.findings-emnlp.29.pdf},
  abstract  = {Automatic analysis of large corpora is a complex task, especially
               in terms of time efficiency. This complexity is increased by the
               fact that flexible, extensible text analysis requires the continuous
               integration of ever new tools. Since there are no adequate frameworks
               for these purposes in the field of NLP, and especially in the
               context of UIMA, that are not outdated or unusable for security
               reasons, we present a new approach to address the latter task:
               Docker Unified UIMA Interface (DUUI), a scalable, flexible, lightweight,
               and feature-rich framework for automatic distributed analysis
               of text corpora that leverages Big Data experience and virtualization
               with Docker. We evaluate DUUI{'}s communication approach against
               a state-of-the-art approach and demonstrate its outstanding behavior
               in terms of time efficiency, enabling the analysis of big text
               data.}
}

@inproceedings{Boenisch:et:al:2023,
  title     = {{Bundestags-Mine}: Natural Language Processing for Extracting
               Key Information from Government Documents},
  isbn      = {9781643684734},
  issn      = {1879-8314},
  url       = {http://dx.doi.org/10.3233/FAIA230996},
  doi       = {10.3233/faia230996},
  booktitle = {Legal Knowledge and Information Systems},
  publisher = {IOS Press},
  author    = {B\"{o}nisch, Kevin and Abrami, Giuseppe and Wehnert, Sabine and Mehler, Alexander},
  year      = {2023}
}

@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}
}

@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},
  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.},
  url       = {https://aclanthology.org/2022.lrec-1.202}
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2022/06/GerParCor_LREC_2022.pdf},
  keywords  = {gerparcor},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.202.pdf}
}

@inproceedings{Henlein:Mehler:2022,
  title     = {What do Toothbrushes do in the Kitchen? How Transformers Think
               our World is Structured},
  author    = {Henlein, Alexander and Mehler, Alexander},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter
               of the Association for Computational Linguistics: Human Language
               Technologies},
  year      = {2022},
  address   = {Seattle, United States},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2022.naacl-main.425},
  doi       = {10.18653/v1/2022.naacl-main.425},
  pages     = {5791--5807},
  abstract  = {Transformer-based models are now predominant in NLP.They outperform
               approaches based on static models in many respects. This success
               has in turn prompted research that reveals a number of biases
               in the language models generated by transformers. In this paper
               we utilize this research on biases to investigate to what extent
               transformer-based language models allow for extracting knowledge
               about object relations (X occurs in Y; X consists of Z; action
               A involves using X).To this end, we compare contextualized models
               with their static counterparts. We make this comparison dependent
               on the application of a number of similarity measures and classifiers.
               Our results are threefold:Firstly, we show that the models combined
               with the different similarity measures differ greatly in terms
               of the amount of knowledge they allow for extracting. Secondly,
               our results suggest that similarity measures perform much worse
               than classifier-based approaches. Thirdly, we show that, surprisingly,
               static models perform almost as well as contextualized models
               {--} in some cases even better.}
}

@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}
}

@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}
}

@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.}
}

@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}
}

@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}
}

@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 17th Joint ACL - ISO Workshop on Interoperable
               Semantic Annotation},
  series    = {ISA-17},
  publisher = {Association for Computational Linguistics},
  address   = {Groningen, The Netherlands (online)},
  month     = {June},
  editor    = {Bunt, Harry},
  year      = {2021},
  url       = {https://aclanthology.org/2021.isa-1.7},
  pages     = {65--75},
  keywords  = {textannotator},
  pdf       = {https://iwcs2021.github.io/proceedings/isa/pdf/2021.isa-1.7.pdf},
  abstract  = {We argue that mainly due to technical innovation in the landscape
               of annotation tools, a conceptual change in annotation models
               and processes is also on the horizon. It is diagnosed that these
               changes are bound up with multi-media and multi-perspective facilities
               of annotation tools, in particular when considering virtual reality
               (VR) and augmented reality (AR) applications, their potential
               ubiquitous use, and the exploitation of externally trained natural
               language pre-processing methods. Such developments potentially
               lead to a dynamic and exploratory heuristic construction of the
               annotation process. With TextAnnotator an annotation suite is
               introduced which focuses on multi-mediality and multi-perspectivity
               with an interoperable set of task-specific annotation modules
               (e.g., for word classification, rhetorical structures, dependency
               trees, semantic roles, and more) and their linkage to VR and mobile
               implementations. The basic architecture and usage of TextAnnotator
               is described and related to the above mentioned shifts in the
               field.}
}

@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}
}

@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}
}

@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},
  keywords  = {biofid}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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},
  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},
  keywords  = {textannotator},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.112.pdf}
}

@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.},
  keywords  = {textannotator},
  poster    = {https://hcommons.org/deposits/download/hc:31816/CONTENT/dh2020_textannotator_poster.pdf}
}

@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},
  keywords  = {biofid}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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},
  keywords  = {textannotator},
  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.}
}

@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}
}

@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}
}

@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}
}

@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}},
  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.},
  keywords  = {biofid}
}

@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.}
}

@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}
}

@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}
}

@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       = {}
}

@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}
}

@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}
}

@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},
  keywords  = {UIMA},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/UIMA-DI.pdf},
  year      = {2018}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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},
  keywords  = {biofid}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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.},
  year      = {2009}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@inproceedings{Mehler:2006:a,
  author    = {Mehler, Alexander},
  title     = {In Search of a Bridge between Network Analysis in Computational
               Linguistics and Computational Biology – A Conceptual Note},
  booktitle = {Proceedings of the 2006 International Conference on Bioinformatics
               \& Computational Biology (BIOCOMP '06), June 26, 2006, Las Vegas,
               USA},
  editor    = {Arabnia, Hamid R. and Valafar, Homayoun},
  pages     = {496-500},
  pdf       = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.92.9842&rep=rep1&type=pdf},
  year      = {2006}
}

@inproceedings{Mehler:Dehmer:Gleim:2006,
  author    = {Mehler, Alexander and Dehmer, Matthias and Gleim, Rüdiger},
  title     = {Towards Logical Hypertext Structure - A Graph-Theoretic Perspective},
  booktitle = {Proceedings of the Fourth International Workshop on Innovative
               Internet Computing Systems (I2CS '04)},
  editor    = {Böhme, Thomas and Heyer, Gerhard},
  series    = {Lecture Notes in Computer Science 3473},
  pages     = {136-150},
  address   = {Berlin/New York},
  publisher = {Springer},
  abstract  = {Facing the retrieval problem according to the overwhelming set
               of documents online the adaptation of text categorization to web
               units has recently been pushed. The aim is to utilize categories
               of web sites and pages as an additional retrieval criterion. In
               this context, the bag-of-words model has been utilized just as
               HTML tags and link structures. In spite of promising results this
               adaptation stays in the framework of IR specific models since
               it neglects the content-based structuring inherent to hypertext
               units. This paper approaches hypertext modelling from the perspective
               of graph-theory. It presents an XML-based format for representing
               websites as hypergraphs. These hypergraphs are used to shed light
               on the relation of hypertext structure types and their web-based
               instances. We place emphasis on two characteristics of this relation:
               In terms of realizational ambiguity we speak of functional equivalents
               to the manifestation of the same structure type. In terms of polymorphism
               we speak of a single web unit which manifests different structure
               types. It is shown that polymorphism is a prevalent characteristic
               of web-based units. This is done by means of a categorization
               experiment which analyses a corpus of hypergraphs representing
               the structure and content of pages of conference websites. On
               this background we plead for a revision of text representation
               models by means of hypergraphs which are sensitive to the manifold
               structuring of web documents.},
  website   = {http://rd.springer.com/chapter/10.1007/11553762_14},
  year      = {2006}
}

@inproceedings{Mehler:Sichelschmidt:2006,
  author    = {Mehler, Alexander and Sichelschmidt, Lorenz},
  title     = {Reconceptualizing Latent Semantic Analysis in Terms of Complex
               Network Theory. A Corpus-Linguistic Approach},
  booktitle = {2nd International Conference of the German Cognitive Linguistics
               Association – Theme Session: Cognitive-Linguistic Approaches:
               What can we gain by computational treatment of data? 5.-7. Oktober
               2006, Ludwig-Maximilians-Universit{\"a}t München},
  pages     = {23-26},
  editors   = {Alonge, Antonietta and Lönneker-Rodman, Birte},
  pdf       = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.87.5069&rep=rep1&type=pdf},
  year      = {2006}
}

@incollection{Mehler:2006:e,
  author    = {Mehler, Alexander},
  title     = {Stratified Constraint Satisfaction Networks in Synergetic Multi-Agent
               Simulations of Language Evolution},
  booktitle = {Artificial Cognition Systems},
  publisher = {Idea Group Inc.},
  editor    = {Loula, Angelo and Gudwin, Ricardo and Queiroz, João},
  pages     = {140-174},
  address   = {Hershey},
  abstract  = {Ehedem = Mehler:2005:e},
  year      = {2006}
}

@inproceedings{Mehler:2006:c,
  author    = {Mehler, Alexander},
  title     = {Text Linkage in the Wiki Medium – A Comparative Study},
  booktitle = {Proceedings of the EACL Workshop on New Text – Wikis and blogs
               and other dynamic text sources, April 3-7, 2006, Trento, Italy},
  editor    = {Karlgren, Jussi},
  pages     = {1-8},
  abstract  = {Workshop organizer: Jussi Karlgren},
  pdf       = {http://www.aclweb.org/anthology/W06-2801},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.6390},
  year      = {2006}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@article{Mehler:2005:a,
  author    = {Mehler, Alexander},
  title     = {Zur textlinguistischen Fundierung der Text- und Korpuskonversion},
  journal   = {Sprache und Datenverarbeitung. International Journal
                   for Language Data Processing},
  volume    = {1},
  pages     = {29-53},
  abstract  = {Die automatische Konversion von Texten in Hypertexte ist mit der
               Erwartung verbunden, computerbasierte Rezeptionshilfen zu gewinnen.
               Dies betrifft insbesondere die Bew{\"a}ltigung der ungeheuren
               Menge an Fachliteratur im Rahmen der Wissenschaftskommunikation.
               Von einem thematisch relevanten Text zu einem thematisch verwandten
               Text per Hyperlink direkt gelangen zu können, stellt einen Anspruch
               dar, dessen Erfüllung mittels digitaler Bibliotheken n{\"a}her
               gerückt zu sein scheint. Doch wie lassen sich die Kriterien, nach
               denen Texte automatisch verlinkt werden, genauer begründen? Dieser
               Beitrag geht dieser Frage aus der Sicht textlinguistischer Modellbildungen
               nach. Er zeigt, dass parallel zur Entwicklung der Textlinguistik,
               wenn auch mit einer gewissen Verzögerung, Konversionsans{\"a}tze
               entwickelt wurden, die sich jeweils an einer bestimmten Stufe
               des Textbegriffs orientieren. Der Beitrag weist nicht nur das
               diesen Ans{\"a}tzen gemeinsame Fundament in Form der so genannten
               Explikationshypothese nach, sondern verweist zugleich auf grundlegende
               Automatisierungsdefizite, die mit ihnen verbunden sind. Mit systemisch-funktionalen
               Hypertexten wird schlie{\ss}lich ein Ansatz skizziert, der darauf
               zielt, den Anspruch nach textlinguistischer Fundierung und Automatisierbarkeit
               zu vereinen.},
  publisher = {GSCL},
  year      = {2005}
}

@inproceedings{Mehler:2005:d,
  author    = {Mehler, Alexander},
  title     = {Lexical Chaining as a Source of Text Chaining},
  booktitle = {Proceedings of the 1st Computational Systemic Functional Grammar
               Conference, University of Sydney, Australia},
  editor    = {Patrick, Jon and Matthiessen, Christian},
  pages     = {12-21},
  abstract  = {July 16, 2005,},
  pdf       = {http://www.www.texttechnologylab.org/media/pdf/CohesionTrees1.pdf},
  year      = {2005}
}

@incollection{Mehler:2005:b,
  author    = {Mehler, Alexander},
  title     = {Eigenschaften der textuellen Einheiten und Systeme / Properties
               of Textual Units and Systems},
  booktitle = {Quantitative Linguistik. Ein internationales Handbuch / Quantitative
               Linguistics. An International Handbook},
  publisher = {De Gruyter},
  editor    = {Köhler, Reinhard and Altmann, Gabriel and Piotrowski, Raijmund G.},
  pages     = {325-348},
  address   = {Berlin/New York},
  year      = {2005}
}

@book{Mehler:Wolff:2005:a,
  author    = {Mehler, Alexander and Wolff, Christian},
  editor    = {Mehler, Alexander and Wolff, Christian},
  title     = {Text Mining},
  publisher = {GSCL},
  volume    = {20(1)},
  series    = {Journal for Language Technology and Computational
                   Linguistics (JLCL)},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/TextMining.png},
  pagetotal = {143},
  website   = {http://www.jlcl.org/2005_Heft1/LDV-Forum1.2005.pdf},
  year      = {2005}
}

@inproceedings{Mehler:Dehmer:Gleim:2005,
  author    = {Mehler, Alexander and Dehmer, Matthias and Gleim, Rüdiger},
  title     = {Zur Automatischen Klassifikation von Webgenres},
  booktitle = {Sprachtechnologie, mobile Kommunikation und linguistische Ressourcen.
               Beitr{\"a}ge zur GLDV-Frühjahrstagung '05, 10. M{\"a}rz – 01.
               April 2005, Universit{\"a}t Bonn},
  editor    = {Fisseni, Bernhard and Schmitz, Hans-Christina and Schröder, Bernhard
               and Wagner, Petra},
  pages     = {158-174},
  address   = {Frankfurt a. M.},
  publisher = {Lang},
  year      = {2005}
}

@book{Mehler:2005:e,
  author    = {Mehler, Alexander},
  editor    = {Mehler, Alexander},
  title     = {Korpuslinguistik},
  volume    = {20(2)},
  series    = {Journal for Language Technology and Computational
                   Linguistics (JLCL)},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/Korpuslinguistik.png},
  pagetotal = {97},
  website   = {http://www.jlcl.org/2005_Heft2/LDV_Forum_Band_20_Heft_2.pdf},
  year      = {2005}
}

@article{Mehler:Wolff:2005:b,
  author    = {Mehler, Alexander and Wolff, Christian},
  title     = {Einleitung: Perspektiven und Positionen des Text Mining},
  journal   = {Journal for Language Technology and Computational
                   Linguistics (JLCL)},
  volume    = {20},
  number    = {1},
  pages     = {1-18},
  abstract  = {Beitr{\"a}ge zum Thema Text Mining beginnen vielfach mit dem Hinweis
               auf die enorme Zunahme online verfügbarer Dokumente, ob nun im
               Internet oder in Intranets (Losiewicz et al. 2000; Merkl 2000;
               Feldman 2001; Mehler 2001; Joachims \& Leopold 2002). Der hiermit
               einhergehenden „Informationsflut“ wird das Ungenügen des Information
               Retrieval (IR) bzw. seiner g{\"a}ngigen Verfahren der Informationsaufbereitung
               und Informationserschlie{\ss}ung gegenübergestellt. Es wird bem{\"a}ngelt,
               dass sich das IR weitgehend darin erschöpft, Teilmengen von Textkollektionen
               auf Suchanfragen hin aufzufinden und in der Regel blo{\ss} listenförmig
               anzuordnen. Das auf diese Weise dargestellte Spannungsverh{\"a}ltnis
               von Informationsexplosion und Defiziten bestehender IR-Verfahren
               bildet den Hintergrund für die Entwicklung von Verfahren zur automatischen
               Verarbeitung textueller Einheiten, die sich st{\"a}rker an den
               Anforderungen von Informationssuchenden orientieren. Anders ausgedrückt:
               Mit der Einführung der Neuen Medien w{\"a}chst die Bedeutung digitalisierter
               Dokumente als Prim{\"a}rmedium für die Verarbeitung, Verbreitung
               und Verwaltung von Information in öffentlichen und betrieblichen
               Organisationen. Dabei steht wegen der Menge zu verarbeitender
               Einheiten die Alternative einer intellektuellen Dokumenterschlie{\ss}ung
               nicht zur Verfügung. Andererseits wachsen die Anforderung an eine
               automatische Textanalyse, der das klassische IR nicht gerecht
               wird. Der Mehrzahl der hiervon betroffenen textuellen Einheiten
               fehlt die explizite Strukturiertheit formaler Datenstrukturen.
               Vielmehr weisen sie je nach Text- bzw. Dokumenttyp ganz unterschiedliche
               Strukturierungsgrade auf. Dabei korreliert die Flexibilit{\"a}t
               der Organisationsziele negativ mit dem Grad an explizierter Strukturiertheit
               und positiv mit der Anzahl jener Texte und Texttypen (E-Mails,
               Memos, Expertisen, technische Dokumentationen etc.), die im Zuge
               ihrer Realisierung produziert bzw. rezipiert werden. Vor diesem
               Hintergrund entsteht ein Bedarf an Texttechnologien, die ihren
               Benutzern nicht nur „intelligente“ Schnittstellen zur Textrezeption
               anbieten, sondern zugleich auf inhaltsorientierte Textanalysen
               zielen, um auf diese Weise aufgabenrelevante Daten explorieren
               und kontextsensitiv aufbereiten zu helfen. Das Text Mining ist
               mit dem Versprechen verbunden, eine solche Technologie darzustellen
               bzw. sich als solche zu entwickeln. Dieser einheitlichen Problembeschreibung
               stehen konkurrierende Textmining-Spezifikationen gegenüber, was
               bereits die Vielfalt der Namensgebungen verdeutlicht. So finden
               sich neben der Bezeichnung Text Mining (Joachims \& Leopold 2002;
               Tan 1999) die Alternativen • Text Data Mining (Hearst 1999b; Merkl
               2000), • Textual Data Mining (Losiewicz et al. 2000), • Text Knowledge
               Engineering (Hahn \& Schnattinger 1998), Knowledge Discovery in
               Texts (Kodratoff 1999) oder Knowledge Discovery in Textual Databases
               (Feldman \& Dagan 1995). Dabei l{\"a}sst bereits die Namensgebung
               erkennen, dass es sich um Analogiebildungen zu dem (nur unwesentlich
               {\"a}lteren) Forschungsgebiet des Data Mining (DM; als Bestandteil
               des Knowledge Discovery in Databases – KDD) handelt. Diese Namensvielfalt
               findet ihre Entsprechung in widerstreitenden Aufgabenzuweisungen.
               So setzt beispielsweise Sebastiani (2002) Informationsextraktion
               und Text Mining weitgehend gleich, wobei er eine Schnittmenge
               zwischen Text Mining und Textkategorisierung ausmacht (siehe auch
               Dörre et al. 1999). Demgegenüber betrachten Kosala \& Blockeel
               (2000) Informationsextraktion und Textkategorisierung lediglich
               als Teilbereiche des ihrer Ansicht nach umfassenderen Text Mining,
               w{\"a}hrend Hearst (1999a) im Gegensatz hierzu Informationsextraktion
               und Textkategorisierung explizit aus dem Bereich des explorativen
               Text Mining ausschlie{\ss}t.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_wolff_2005_b.pdf},
  website   = {http://epub.uni-regensburg.de/6844/},
  year      = {2005}
}

@inproceedings{Mehler:Gleim:2005:a,
  author    = {Mehler, Alexander and Gleim, Rüdiger},
  title     = {Polymorphism in Generic Web Units. A corpus linguistic study},
  booktitle = {Proceedings of Corpus Linguistics '05, July 14-17, 2005, University
               of Birmingham, Great Britian},
  volume    = {Corpus Linguistics Conference Series 1(1)},
  abstract  = {Corpus linguistics and related disciplines which focus on statistical
               analyses of textual units have substantial need for large corpora.
               More specifically, genre or register specific corpora are needed
               which allow studying variations in language use. Along with the
               incredible growth of the internet, the web became an important
               source of linguistic data. Of course, web corpora face the same
               problem of acquiring genre specific corpora. Amongst other things,
               web mining is a framework of methods for automatically assigning
               category labels to web units and thus may be seen as a solution
               to this corpus acquisition problem as far as genre categories
               are applied. The paper argues that this approach is faced with
               the problem of a many-to-many relation between expression units
               on the one hand and content or function units on the other hand.
               A quantitative study is performed which supports the argumentation
               that functions of web-based communication are very often concentrated
               on single web pages and thus interfere any effort of directly
               applying the classical apparatus of categorization on web page
               level. The paper outlines a two-level algorithm as an alternative
               approach to category assignment which is sensitive to genre specific
               structures and thus may be used to tackle the problem of acquiring
               genre specific corpora.},
  issn      = {1747-9398},
  pdf       = {http://www.birmingham.ac.uk/Documents/college-artslaw/corpus/conference-archives/2005-journal/Thewebasacorpus/AlexanderMehlerandRuedigerGleimCorpusLinguistics2005.pdf},
  year      = {2005}
}

@inproceedings{Mehler:2005:c,
  author    = {Mehler, Alexander},
  title     = {Preliminaries to an Algebraic Treatment of Lexical Associations},
  booktitle = {Learning and Extending Lexical Ontologies. Proceedings of the
               Workshop at the 22nd International Conference on Machine Learning
               (ICML '05), August 7-11, 2005, Universit{\"a}t Bonn, Germany},
  editor    = {Biemann, Chris and Paa{\ss}, Gerhard},
  pages     = {41-47},
  year      = {2005}
}

@inproceedings{Dehmer:Emmert:Streib:Mehler:Kilian:Muehlhaeuser:2005,
  author    = {Dehmer, Matthias and Emmert-Streib, Frank and Mehler, Alexander
               and Kilian, Jürgen and Mühlh{\"a}user, Max},
  title     = {Application of a similarity measure for graphs to web-based document structures},
  booktitle = {Proceedings of VI. International Conference on Enformatika, Systems
               Sciences and Engineering, Budapest, Hungary, October 2005, International
               Academy of Sciences: Enformatika 8 (2005)},
  pages     = {77-81},
  abstract  = {Due to the tremendous amount of information provided by the World
               Wide Web (WWW) developing methods for mining the structure of
               web-based documents is of considerable interest. In this paper
               we present a similarity measure for graphs representing web-based
               hypertext structures. Our similarity measure is mainly based on
               a novel representation of a graph as linear integer strings, 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 for solving a novel and challenging
               problem: Measuring the structural similarity of generalized trees.
               In other words: 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 for developing a efficient graph similarity measure. We
               demonstrate that our similarity measure captures important structural
               information by applying it to two different test sets consisting
               of graphs representing web-based document structures.},
  pdf       = {http://waset.org/publications/15299/application-of-a-similarity-measure-for-graphs-to-web-based-document-structures},
  website   = {https://www.researchgate.net/publication/238687277_Application_of_a_Similarity_Measure_for_Graphs_to_Web-based_Document_Structures},
  year      = {2005}
}

@incollection{Mehler:2003:d,
  author    = {Mehler, Alexander},
  title     = {Textmodellierung: Mehrstufige Modellierung generischer Bausteine
               der Text{\"a}hnlichkeitsmessung},
  booktitle = {Automatische Textanalyse: Systeme und Methoden zur Annotation
               und Analyse natürlichsprachlicher Texte},
  publisher = {Verlag für Sozialwissenschaften},
  editor    = {Mehler, Alexander and Lobin, Henning},
  pages     = {101-120},
  address   = {Wiesbaden},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/AutomatischeTextanalyse2.jpg},
  year      = {2004}
}

@inproceedings{Dehmer:Mehler:Gleim:2004,
  author    = {Dehmer, Matthias and Mehler, Alexander and Gleim, Rüdiger},
  title     = {Aspekte der Kategorisierung von Webseiten},
  booktitle = {INFORMATIK 2004 – Informatik verbindet, Band 2, Beitr{\"a}ge der
               34. Jahrestagung der Gesellschaft für Informatik e.V. (GI). Workshop
               Multimedia-Informationssysteme},
  editor    = {Dadam, Peter and Reichert, Manfred},
  volume    = {51},
  series    = {Lecture Notes in Informatics},
  pages     = {39-43},
  publisher = {GI},
  abstract  = {Im Zuge der Web-basierten Kommunikation tritt die Frage auf, inwiefern
               Webpages zum Zwecke ihrer inhaltsorientierten Filterung kategorisiert
               werden können. Diese Studie untersucht zwei Ph{\"a}nomene, welche
               die Bedingung der Möglichkeit einer solchen Kategorisierung betreffen
               (siehe [6]): Mit dem Begriff der funktionalen Aquivalenz beziehen
               wir uns auf das Ph{\"a}nomen, dass dieselbe Funktions- oder Inhaltskategorie
               durch völlig verschiedene Bausteine Web-basierter Dokumente manifestiert
               werden kann. Mit dem Begriff des Polymorphie beziehen wir uns
               auf das Ph{\"a}nomen, dass dasselbe Dokument zugleich mehrere
               Funktions- oder Inhaltskategorien manifestieren kann. Die zentrale
               Hypothese lautet, dass beide Ph{\"a}nomene für Web-basierte Hypertextstrukturen
               charakteristisch sind. Ist dies der Fall, so kann die automatische
               Kategorisierung von Hypertexten [2, 10] nicht mehr als eindeutige
               Zuordnung verstanden werden, bei der einem Dokument genau eine
               Kategorie zugeordnet wird. In diesem Sinne thematisiert das Papier
               die Frage nach der ad{\"a}quaten Modellierung multimedialer Dokumente.},
  pdf       = {http://subs.emis.de/LNI/Proceedings/Proceedings51/GI-Proceedings.51-11.pdf},
  website   = {https://www.researchgate.net/publication/221385316_Aspekte_der_Kategorisierung_von_Webseiten},
  year      = {2004}
}

@article{Mehler:2004:b,
  author    = {Mehler, Alexander},
  title     = {Automatische Synthese Internet-basierter Links für digitale Bibliotheken},
  journal   = {Osnabrücker Beitr{\"a}ge zur Sprachtheorie.
                   Themenheft Internetbasierte Kommunikation},
  volume    = {68},
  pages     = {31-53},
  abstract  = {Dieser Beitrag behandelt Verfahren zur automatischen Erzeugung
               von Hyperlinks, wie sie im WWW für die Informationssuche bereitstehen.
               Dabei steht die Frage im Vordergrund, auf welche Weise bestehende
               Verfahren suchrelevante Dokumente bestimmen und von diesen aus
               inhaltsverwandte Dokumente verlinken. Dieser Gegenstand verbindet
               den Bereich des klassischen Information Retrievals (IR) mit einem
               Anwendungsgebiet, das in der Wissenschaftskommunikation unter
               dem Stichwort der digitalen Bibliothek unter Nutzbarmachung des
               Hyperlink-basierten Browsings firmiert. Ein Beispiel hierfür bildet
               die digitale Bibliothek CiteSeer (Lawrence et al. 1999), welche
               das Boolesche Retrieval dadurch erweitert, dass ausgehend von
               Treffern einer Suche jene Dokumente per Link angesteuert werden
               können, welche die aufgefundenen Dokumente zitieren oder von diesen
               zitiert werden. CiteSeer ist also ein System, welches das Schlagwort-basierte
               Querying im Rahmen des klassischen IRs mit dem Hypertext-basierten
               Browsing von Zitaten verknüpft, und zwar zu dem Zweck, die Suche
               wissenschaftlicher Dokumente zu erleichtern. Darüber hinaus verwendet
               es die unter dem Stichwort des Vektorraummodells bekannt gewordene
               Technologie für den wortbasierten Vergleich von Texten. Der Beitrag
               setzt an dieser Stelle an. Er argumentiert, dass Verfahren bereitstehen,
               welche die Anforderung nach inhaltsorientiertem Retrieval mit
               dem inhaltsorientierten Browsing verbinden, mit der Forderung
               also, dass Hyperlinks, die E-Texte als digitalisierte Versionen
               von (wissenschaftlichen) Dokumenten verknüpfen (Storrer 2002),
               Inhalts- und nicht nur Zitat-basiert sind.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2004_b.pdf},
  year      = {2004}
}

@inproceedings{Mehler:2004:c,
  author    = {Mehler, Alexander},
  title     = {A Data-Oriented Model of Context in Hypertext Authoring},
  booktitle = {Proceedings of the 7th International Workshop on Organisational
               Semiotics (OS '04), July 19-20, 2004, Setúbal, Portugal},
  editor    = {Filipe, Joaquim and Liu, Kecheng},
  pages     = {24-45},
  address   = {Setúbal},
  publisher = {INSTICC},
  pdf       = {http://www.orgsem.org/papers/02.pdf},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.7944},
  year      = {2004}
}

@book{Mehler:Lobin:2004:a,
  author    = {Mehler, Alexander and Lobin, Henning},
  editor    = {Mehler, Alexander and Lobin, Henning},
  title     = {Automatische Textanalyse. Systeme und Methoden zur Annotation
               und Analyse natürlichsprachlicher Texte},
  publisher = {Verlag für Sozialwissenschaften},
  address   = {Wiesbaden},
  pagetotal = {290},
  website   = {http://www.v-r.de/de/Mehler-Lobin-Automatische-Textanalyse/t/352526527/},
  year      = {2004}
}

@incollection{Mehler:Lobin:2004:b,
  author    = {Mehler, Alexander and Lobin, Henning},
  title     = {Aspekte der texttechnologischen Modellierung},
  booktitle = {Automatische Textanalyse: Systeme und Methoden zur Annotation
               und Analyse natürlichsprachlicher Texte},
  publisher = {Verlag für Sozialwissenschaften},
  editor    = {Mehler, Alexander and Lobin, Henning},
  pages     = {1-21},
  address   = {Wiesbaden},
  year      = {2004}
}

@incollection{Mehler:2004:h,
  author    = {Mehler, Alexander},
  title     = {Textmining},
  booktitle = {Texttechnologie. Perspektiven und Anwendungen},
  publisher = {Stauffenburg},
  editor    = {Lobin, Henning and Lemnitzer, Lothar},
  pages     = {329-352},
  address   = {Tübingen},
  year      = {2004}
}

@article{Mehler:2003:c,
  author    = {Mehler, Alexander},
  title     = {Ein Kompositionalit{\"a}tsprinzip für numerische Textsemantiken},
  journal   = {Journal for Language Technology and Computational
                   Linguistics (JLCL)},
  volume    = {18},
  number    = {1-2},
  pages     = {321-337},
  abstract  = {Der Beitrag beschreibt eine Variante des Kompositionalit{\"a}tsprinzips
               der Bedeutung als Grundprinzip für die numerische Analyse unsystematischer
               Sinnrelationen komplexer Zeichen, das über das Ph{\"a}nomen der
               perspektivischen Interpretation hinaus gebrauchssemantische Bedeutungsaspekte
               berücksichtigt. Ziel ist es, ein theoretisches Fundament für korpusanalytische
               Ans{\"a}tze in der Semantik, die oftmals die linguistische Interpretierbarkeit
               ihrer Analyseergebnisse vermissen lassen, zu umrei{\ss}en. Die
               Spezifikation des Kompositionalit{\"a}tsprinzips erfolgt unter
               Rekurs auf das Modell eines hierarchisch geordneten Constraint-Satisfaction-Prozesses.
               Hiermit ist das l{\"a}ngerfristige Ziel verbunden, das Problem
               einer defizit{\"a}ren numerischen Textrepr{\"a}sentation sowie
               die mangelnde Integration von propositionaler und strukturaler
               bzw. korpusanalytischer Semantik anzugehen. Die Erörterungen dieses
               Beitrags sind prim{\"a}r konzeptioneller Natur; sie betreffen
               die Konzeption einer numerischen Textsemantik zur Vermeidung von
               Defiziten bestehender Ans{\"a}tze.},
  pdf       = {http://media.dwds.de/jlcl/2003_Doppelheft/321-337_Mehler.pdf},
  year      = {2003}
}

@inproceedings{Mehler:Reich:2003,
  author    = {Mehler, Alexander and Reich, Siegfried},
  title     = {Guided Tours + Trails := Guided Trails},
  booktitle = {Poster at the 14th ACM Conference on Hypertext and Hypermedia
               (Hypertext '03), Nottingham, August 26-30},
  pages     = {1-2},
  website   = {http://www.sigweb.org/Ht03posters},
  year      = {2003}
}

@incollection{Mehler:2003,
  author    = {Mehler, Alexander},
  title     = {Konnotative Textbedeutungen: zur Modellierung struktureller Aspekte
               der Bedeutungen von Texten},
  booktitle = {Korpuslinguistische Untersuchungen zur quantitativen und systemtheoretischen
               Linguistik},
  publisher = {Gardez! Verlag},
  editor    = {Köhler, Reinhard},
  pages     = {320-347},
  address   = {Sankt Augustin},
  pdf       = {http://ubt.opus.hbz-nrw.de/volltexte/2004/279/pdf/10_mehler.pdf},
  year      = {2003}
}

@article{Mehler:2003:b,
  author    = {Mehler, Alexander},
  title     = {Methodological Aspects of Computational Semiotics},
  journal   = {SEED Journal},
  volume    = {3},
  number    = {3},
  pages     = {71-80},
  abstract  = {In the following, elementary constituents of models in computational
               semiotics are outlined. This is done by referring to computer
               simulations as a framework which neither aims to describe artificial
               sign systems (as done in computer semiotics), nor to realize semiotic
               functions in “artificial worlds” (as proposed in “artificial semiosis”).
               Rather, the framework referred to focuses on preconditions of
               computer-based simulations of semiotic processes. Following this
               approach, the paper focuses on methodological aspects of computational
               semiotics.},
  year      = {2003}
}

@incollection{Mehler:2002:b,
  author    = {Mehler, Alexander},
  title     = {Textbedeutungsrekonstruktion. Grundzüge einer Architektur zur
               Modellierung der Bedeutungen von Texten},
  booktitle = {Prozesse der Bedeutungskonstruktion},
  publisher = {Peter Lang},
  editor    = {Pohl, Inge},
  pages     = {445-486},
  address   = {Frankfurt a. M.},
  year      = {2002}
}

@article{Mehler:2002:a,
  author    = {Mehler, Alexander},
  title     = {Hierarchical Analysis of Text Similarity Data},
  journal   = {Künstliche Intelligenz (KI)},
  volume    = {2},
  pages     = {12-16},
  abstract  = {Semantic spaces are used as a representational format for modeling
               similarities of signs. As a multidimensional data structure they
               are bound to the question of how to explore similarity relations
               of signs mapped onto them. This paper introduces an abstract data
               structure called dependency scheme as a formal format which encapsulates
               two types of order relations, whose variable instatiation allows
               to derive different classes of trees for the hierarchial analysis
               of text similarity data derived from semantic spaces.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2002_a.pdf},
  year      = {2002}
}

@inproceedings{Mehler:2002:k,
  author    = {Mehler, Alexander},
  title     = {Hierarchical Orderings of Textual Units},
  booktitle = {Proceedings of the 19th International Conference on Computational
               Linguistics (COLING '02), August 24 – September 1, 2002, Taipei,
               Taiwan},
  pages     = {646-652},
  address   = {San Francisco},
  publisher = {Morgan Kaufmann},
  abstract  = {Text representation is a central task for any approach to automatic
               learning from texts. It requires a format which allows to interrelate
               texts even if they do not share content words, but deal with similar
               topics. Furthermore, measuring text similarities raises the question
               of how to organize the resulting clusters. This paper presents
               cohesion trees (CT) as a data structure for the perspective, hierarchical
               organization of text corpora. CTs operate on alternative text
               representation models taking lexical organization, quantitative
               text characteristics, and text structure into account. It is shown
               that CTs realize text linkages which are lexically more homogeneous
               than those produced by minimal spanning trees.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_2002_k.pdf},
  year      = {2002}
}

@inproceedings{Mehler:2002:f,
  author    = {Mehler, Alexander},
  title     = {Cohesive Paths: Applying the Concept of Cohesion to Hypertext},
  booktitle = {Sprachwissenschaft auf dem Weg in das dritte Jahrtausend. Proceedings
               of the 34th Linguistics Colloquium, September 7-10, 1999, Universit{\"a}t
               Mainz},
  editor    = {Rapp, Reinhard},
  pages     = {725-733},
  address   = {Frankfurt a. M.},
  publisher = {Peter Lang},
  year      = {2002}
}

@inproceedings{Mehler:2002:e,
  author    = {Mehler, Alexander},
  title     = {Text Mining with the Help of Cohesion Trees},
  booktitle = {Classification, Automation, and New Media. Proceedings of the
               24th Annual Conference of the Gesellschaft für Klassifikation,
               March 15-17, 2000, Universit{\"a}t Passau},
  editor    = {Gaul, Wolfgang and Ritter, Gunter},
  pages     = {199-206},
  address   = {Berlin/New York},
  publisher = {Springer},
  abstract  = {In the framework of automatic text processing, semantic spaces
               are used as a format for modeling similarities of natural language
               texts represented as vectors. They prove to be efficient in divergent
               areas, as information retrieval (Dumais 1995), computational psychology
               (Landauer, Dumais 1997), and computational linguistics (Rieger
               1995; Mehler 1998). In order to group semantically similar texts,
               cluster analysis is used. A central problem of this method relates
               to the difficulty to name clusters, whereas lists neglect the
               polyhierarchical structure of semantic spaces. This paper introduces
               the concept of cohesion tree as an alternative tool for exploring
               similarity relations of texts represented in high dimensional
               spaces. Cohesion trees allow the perspective evaluation of numerically
               represented text similarities. They depart from minimal spanning
               trees (MST) by context-sensitively optimizing path costs. This
               central property underlies the linguistic interpretation of cohesion
               trees: instead of manifesting context-free associations, they
               model context priming effects.},
  website   = {http://www.springerlink.com/content/x484814744877078/},
  year      = {2002}
}

@inproceedings{Mehler:Clarke:2002,
  author    = {Mehler, Alexander and Clarke, Rodney},
  title     = {Systemic Functional Hypertexts. An Architecture for Socialsemiotic
               Hypertext Systems},
  booktitle = {New Directions in Humanities Computing. The 14th Joint International
               Conference of the Association for Literary and Linguistic Computing
               and the Association for Computers and the Humanities (ALLC/ACH
               '02), July 24-28, University of Tübingen},
  pages     = {68-69},
  year      = {2002}
}

@article{Mehler:2002:l,
  author    = {Mehler, Alexander},
  title     = {Components of a Model of Context-Sensitive Hypertexts},
  journal   = {Journal of Universal Computer Science (J.UCS)},
  volume    = {8},
  number    = {10},
  pages     = {924-943},
  abstract  = {On the background of rising Intranet applications the automatic
               generation of adaptable, context-sensitive hypertexts becomes
               more and more important [El-Beltagy et al., 2001]. This observation
               contradicts the literature on hypertext authoring, where Information
               Retrieval techniques prevail, which disregard any linguistic and
               context-theoretical underpinning. As a consequence, resulting
               hypertexts do not manifest those schematic structures, which are
               constitutive for the emergence of text types and the context-mediated
               understanding of their instances, i.e. natural language texts.
               This paper utilizes Systemic Functional Linguistics (SFL) and
               its context model as a theoretical basis of hypertext authoring.
               So called Systemic Functional Hypertexts (SFHT) are proposed,
               which refer to a stratified context layer as the proper source
               of text linkage. The purpose of this paper is twofold: First,
               hypertexts are reconstructed from a linguistic point of view as
               a kind of supersign, whose constituents are natural language texts
               and whose structuring is due to intra- and intertextual coherence
               relations and their context-sensitive interpretation. Second,
               the paper prepares a formal notion of SFHTs as a first step towards
               operationalization of fundamental text linguistic concepts. On
               this background, SFHTs serve to overcome the theoretical poverty
               of many approaches to link generation.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/mehler_components_2002.pdf},
  website   = {http://www.jucs.org/jucs_8_10/components_of_a_model},
  year      = {2002}
}

@incollection{Mehler:Clarke:2001,
  author    = {Mehler, Alexander and Clarke, Rodney},
  title     = {Systemic Functional Hypertexts (SFHT): Modeling Contexts in Hypertexts},
  booktitle = {Organizational Semiotics. Evolving a Science of Information Systems},
  publisher = {Kluwer},
  editor    = {Liu, Kecheng and Clarke, Rodney J. and Andersen, Peter B. and Stamper, Ronald K.},
  pages     = {153-170},
  address   = {Boston},
  abstract  = {IFIP TC8 / WG8.1 Working Conference on Organizational Semiotics.
               July 23-25, 2001, Montreal, Canada},
  website   = {http://link.springer.com/chapter/10.1007/978-0-387-35611-2_10},
  year      = {2001}
}

@book{Mehler:2001:a,
  author    = {Mehler, Alexander},
  title     = {Textbedeutung. Zur prozeduralen Analyse und Repr{\"a}sentation
               struktureller {\"A}hnlichkeiten von Texten / Text Meaning – Procedural
               Analysis and Representation of Structural Similarities of Texts},
  publisher = {Peter Lang},
  volume    = {5},
  series    = {Computer Studies in Language and Speech},
  address   = {Frankfurt a. M.},
  note      = {Zugl. Diss. Univ. Trier},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/38648_cover_front.jpg},
  pagetotal = {401},
  website   = {https://www.peterlang.com/view/product/39259?tab=toc&format=PBK},
  year      = {2001}
}

@article{Mehler:2001:b,
  author    = {Mehler, Alexander},
  title     = {Aspects of Text Mining. From Computational Semiotics to Systemic
               Functional Hypertexts},
  journal   = {Australasian Journal of Information Systems (AJIS)},
  volume    = {8},
  number    = {2},
  pages     = {129-141},
  abstract  = {The significance of natural language texts as the prime information
               structure for the management and dissemination of knowledge in
               organisations is still increasing. Making relevant documents available
               depending on varying tasks in different contexts is of primary
               importance for any efficient task completion. Implementing this
               demand requires the content based processing of texts, which enables
               to reconstruct or, if necessary, to explore the relationship of
               task, context and document. Text mining is a technology that is
               suitable for solving problems of this kind. In the following,
               semiotic aspects of text mining are investigated. Based on the
               primary object of text mining - natural language lexis - the specific
               complexity of this class of signs is outlined and requirements
               for the implementation of text mining procedures are derived.
               This is done with reference to text linkage introduced as a special
               task in text mining. Text linkage refers to the exploration of
               implicit, content based relations of texts (and their annotation
               as typed links in corpora possibly organised as hypertexts). In
               this context, the term systemic functional hypertext is introduced,
               which distinguishes genre and register layers for the management
               of links in a poly-level hypertext system},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Mehler_AJIS-2001.pdf},
  website   = {http://journal.acs.org.au/index.php/ajis/article/view/249/220},
  year      = {2001}
}

@inproceedings{Mehler:1999,
  author    = {Mehler, Alexander},
  title     = {Aspects of Text Semantics in Hypertext},
  booktitle = {Returning to our Diverse Roots. Proceedings of the 10th ACM Conference
               on Hypertext and Hypermedia (Hypertext '99), February 21-25, 1999,
               Technische Universit{\"a}t Darmstadt},
  editor    = {Tochtermann, Klaus and Westbomke, Jörg and Wiil, Uffe K. and Leggett, John J.},
  pages     = {25-26},
  address   = {New York},
  publisher = {ACM Press},
  pdf       = {{http://dl.acm.org/ft_gateway.cfm?id=294477&ftid=30049&dwn=1&CFID=722943569&CFTOKEN=97409508}},
  website   = {http://dl.acm.org/citation.cfm?id=294477},
  year      = {1999}
}

@inproceedings{Clarke:Mehler:1999,
  author    = {Clarke, Rodney and Mehler, Alexander},
  title     = {Theorising Print Media in Contexts: A Systemic Semiotic Contribution
               to Computational Semiotics},
  booktitle = {Proceedings of the 7th International Congress of the IASS-AIS:
               International Association for Semiotic Studies – Sign Processes
               in Complex Systems, Dresden, University of Technology, October
               6-11},
  year      = {1999}
}