Publications

@inproceedings{Luecking:Ginzburg:2025-mass-nouns,
  title     = {Postmodern Quantification with Stuff},
  author    = {Lücking, Andy and Ginzburg, Jonathan},
  booktitle = {Proceedings of \textit{Sinn und Bedeutung}},
  volume    = {29},
  series    = {SuB'29},
  year      = {2025},
  pubstate  = {forthcoming},
  note      = {Forthcoming}
}

@article{Bagci:et:al:2025,
  author    = {Bagci, Mevl{\"u}t and Mehler, Alexander and Abrami, Giuseppe and Schrottenbacher, Patrick
               and Spiekermann, Christian and Konca, Maxim and Schreiber, Jakob and Saukel, Kevin
               and Quintino, Marc and Engel, Juliane},
  title     = {Simulation-Based Learning in Virtual Reality: Three Use Cases
               from Social Science and Technological Foundations in Terms of
               Va.Si.Li-Lab},
  journal   = {Technology, Knowledge and Learning},
  publisher = {Springer Nature},
  year      = {2025},
  month     = {April},
  day       = {01},
  abstract  = {This article examines the predictability of communication scenarios
               within the context of simulation-based learning in virtual reality
               (VR). The aim is to investigate multimodal patterns of social
               interaction that accompany human communication in conflict situations.
               Understanding these patterns can ultimately enhance educational
               technologies' ability to address problematic learning situations
               and support learners in benefiting from VR-based learning. To
               achieve this, the system must accurately predict the task context.
               A central goal of this article is to shed light on this potential.
               Additionally, our research extends to visual communication beyond
               purely linguistic interactions, aiming to enhance VR immersion
               in communicative practices. To this end, the article examines
               the associations between multimodal information units generated
               by individuals interacting in three distinct learning scenarios:
               work organization, school pedagogy, and social life. Several experiments
               demonstrate that predictability exists when multimodal communication
               is analyzed at the level of eight coarse-grained modalities, including
               speech, head and body movements, and gestures. The interactions
               are observed in VR using Va.Si.Li-Lab, a simulation-based system
               that virtualizes learning scenarios, enabling participants to
               collaboratively manage potentially conflicting tasks through multimodal
               communication (Mehler et al. in: Duffy (ed) Digital human modeling
               and applications in health, safety, ergonomics and risk management,
               Springer Nature Switzerland, Cham, 2023). The article discusses
               the technology underlying Va.Si.Li-Lab, its database, and the
               post-processing of interaction data, including speech data. It
               provides theoretical motivation for the application scenarios
               and presents experimental data to illustrate the system's usefulness.
               Based on these data, the article details experiments on the multimodal
               detection of social scenarios, positioning Va.Si.Li-Lab as a use
               case in simulation-based learning.},
  issn      = {2211-1670},
  doi       = {10.1007/s10758-025-09837-7},
  url       = {https://doi.org/10.1007/s10758-025-09837-7}
}

@inproceedings{Boenisch:et:al:2025,
  title     = {Towards Unified, Dynamic and Annotation-based Visualisations and
               Exploration of Annotated Big Data Corpora with the Help of Unified
               Corpus Explorer},
  author    = {Kevin B{\"o}nisch and Giuseppe Abrami and Alexander Mehler},
  booktitle = {2025 Annual Conference of the North American Chapter of the Association
               for Computational Linguistics -- System Demonstration Track},
  year      = {2025},
  keywords  = {uce,biofid},
  video     = {https://www.youtube.com/watch?v=f3kB9pNPjsk},
  note      = {accepted, Best Demo Award}
}

@incollection{Luecking:2025-deixis,
  booktitle = {Wörterbücher zur Sprach- und Kommunikationswissenschaft (WSK)
               -- Semantik und Pragmatik},
  editor    = {Gutzmann, Daniel and Turgay, Katharina and Zimmermann, Thomas Ede},
  doi       = {10.1515/wsk},
  title     = {Deixis},
  author    = {Lücking, Andy},
  year      = {2025},
  publisher = {De Gruyter},
  pubstate  = {forthcoming},
  note      = {Forthcoming}
}

@article{Luecking:Ginzburg:2025-exceptions,
  author    = {Lücking, Andy and Ginzburg, Jonathan},
  title     = {Exceptions From Rules and Noteworthy Exceptions},
  subtitle  = {The Balance Scale for Making Exceptions},
  journal   = {Linguistics and Philosophy},
  year      = {2025},
  pubstate  = {forthcoming},
  note      = {Forthcoming}
}

@article{Abrami:et:al:2025:a,
  title     = {Docker Unified UIMA Interface: New perspectives for NLP on big data},
  journal   = {SoftwareX},
  volume    = {29},
  pages     = {102033},
  year      = {2025},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2024.102033},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711024004047},
  author    = {Giuseppe Abrami and Markos Genios and Filip Fitzermann and Daniel Baumartz
               and Alexander Mehler},
  keywords  = {duui, Docker, Kubernetes, UIMA, Distributed NLP},
  abstract  = {Processing large amounts of natural language text using machine
               learning-based models is becoming important in many disciplines.
               This demand is being met by a variety of approaches, resulting
               in the heterogeneous deployment of separate, partly incompatible,
               not natively scalable applications. To overcome the technological
               bottleneck involved, we have developed Docker Unified UIMA Interface,
               a system for the standardized, parallel, platform-independent,
               distributed and microservices-based solution for processing large
               and extensive text corpora with any NLP method. We present DUUI
               as a framework that enables automated orchestration of GPU-based
               NLP processes beyond the existing Docker Swarm cluster variant,
               and in addition to the adaptation to new runtime environments
               such as Kubernetes. Therefore, a new driver for DUUI is introduced,
               which enables the lightweight orchestration of DUUI processes
               within a Kubernetes environment in a scalable setup. In this way,
               the paper opens up novel text-technological perspectives for existing
               practices in disciplines that deal with the scientific analysis
               of large amounts of data based on NLP.}
}

@inproceedings{Abrami:et:al:2025:b,
  author    = {Abrami, Giuseppe and Baumartz, Daniel and Mehler, Alexander},
  title     = {DUUI: A Toolbox for the Construction of a new Kind of Natural
               Language Processing},
  year      = {2025},
  booktitle = {Proceedings of the DHd 2025: Under Construction. Geisteswissenschaften
               und Data Humanities},
  numpages  = {3},
  location  = {Bielefeld, Germany},
  series    = {DHd 2025},
  publisher = {Zenodo},
  keywords  = {duui},
  pages     = {446--448},
  doi       = {10.5281/zenodo.14943128},
  url       = {https://doi.org/10.5281/zenodo.14943128},
  poster    = {https://zenodo.org/records/14944575}
}

@article{Schrottenbacher:et:al:2025,
  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    = {31},
  number    = {1-2},
  pages     = {76--105},
  year      = {2025},
  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.}
}

@article{Boenisch:et:al:2025: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}},
  journal   = {New Review of Hypermedia and Multimedia},
  volume    = {31},
  number    = {1-2},
  pages     = {45--75},
  year      = {2025},
  publisher = {Taylor \& Francis},
  doi       = {10.1080/13614568.2024.2383581},
  url       = {https://doi.org/10.1080/13614568.2024.2383581},
  eprint    = {https://doi.org/10.1080/13614568.2024.2383581}
}

@misc{Abusaleh:Rahim:2024,
  title     = {A Multitask VAE for Time Series Preprocessing and Prediction of
               Blood Glucose Level},
  author    = {Ali Abusaleh and Mehdi Rahim},
  year      = {2024},
  eprint    = {2410.00015},
  archiveprefix = {arXiv},
  primaryclass = {eess.SP},
  url       = {https://arxiv.org/abs/2410.00015}
}

@article{Owoyele:et:al:2020,
  title     = {Socio-Semantic X-Ray of Multi-Actor Constellations using Topics
               and Interstitial Authors: A Toolkit for Augmenting Computational
               Literature Reviews},
  author    = {Owoyele, Babajide and Verma, Bhuvanesh and Omolaoye, Victor and Edelman, Jonathan Antonio
               and Loorbach, Derk and de Melo, Gerard},
  journal   = {Available at SSRN 4713155},
  doi       = {10.2139/ssrn.4713155},
  url       = {https://dx.doi.org/10.2139/ssrn.4713155},
  year      = {2024}
}

@misc{Owoyele:et:al:2024,
  title     = {MaskAnyone Toolkit: Offering Strategies for Minimizing Privacy
               Risks and Maximizing Utility in Audio-Visual Data Archiving},
  author    = {Babajide Alamu Owoyele and Martin Schilling and Rohan Sawahn and Niklas Kaemer
               and Pavel Zherebenkov and Bhuvanesh Verma and Wim Pouw and Gerard de Melo},
  year      = {2024},
  eprint    = {2408.03185},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url       = {https://arxiv.org/abs/2408.03185}
}

@misc{Verma:Raithel:2024,
  title     = {DFKI-NLP at SemEval-2024 Task 2: Towards Robust LLMs Using Data
               Perturbations and MinMax Training},
  author    = {Bhuvanesh Verma and Lisa Raithel},
  year      = {2024},
  eprint    = {2405.00321},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url       = {https://arxiv.org/abs/2405.00321}
}

@inproceedings{Raithel:et:al:2024,
  title     = {Overview of {\#}{SMM}4{H} 2024 {--} Task 2: Cross-Lingual Few-Shot
               Relation Extraction for Pharmacovigilance in {F}rench, {G}erman,
               and {J}apanese},
  author    = {Raithel, Lisa and Thomas, Philippe and Verma, Bhuvanesh and Roller, Roland
               and Yeh, Hui-Syuan and Yada, Shuntaro and Grouin, Cyril and Wakamiya, Shoko
               and Aramaki, Eiji and M{\"o}ller, Sebastian and Zweigenbaum, Pierre},
  editor    = {Xu, Dongfang and Gonzalez-Hernandez, Graciela},
  booktitle = {Proceedings of The 9th Social Media Mining for Health Research
               and Applications (SMM4H 2024) Workshop and Shared Tasks},
  month     = {aug},
  year      = {2024},
  address   = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2024.smm4h-1.39/},
  pages     = {170--182},
  abstract  = {This paper provides an overview of Task 2 from the Social Media
               Mining for Health 2024 shared task ({\#}SMM4H 2024), which focused
               on Named Entity Recognition (NER, Subtask 2a) and the joint task
               of NER and Relation Extraction (RE, Subtask 2b) for detecting
               adverse drug reactions (ADRs) in German, Japanese, and French
               texts written by patients. Participants were challenged with a
               few-shot learning scenario, necessitating models that can effectively
               generalize from limited annotated examples. Despite the diverse
               strategies employed by the participants, the overall performance
               across submissions from three teams highlighted significant challenges.
               The results underscored the complexity of extracting entities
               and relations in multi-lingual contexts, especially from the noisy
               and informal nature of user-generated content. Further research
               is required to develop robust systems capable of accurately identifying
               and associating ADR-related information in low-resource and multilingual
               settings.}
}

@inbook{Mehler:et:al:2024:a,
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Konca, Maxim and Abrami, Giuseppe and B{\"o}nisch, Kevin
               and Stoeckel, Manuel and Spiekermann, Christian and Engel, Juliane},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Towards New Data Spaces for the Study of Multiple Documents with
               Va.Si.Li-Lab: A Conceptual Analysis},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {259--303},
  abstract  = {The constitution of multiple documents has so far been studied
               essentially as a process in which a single learner consults a
               number (of segments) of different documents in the context of
               the task at hand in order to construct a mental model for the
               purpose of completing the task. As a result of this research focus,
               the constitution of multiple documents appears predominantly as
               a monomodal, non-interactive process in which mainly textual units
               are studied, supplemented by images, text-image relations and
               comparable artifacts. This approach is reflected in the contextual
               fixity of the research design, in which the learners under study
               search for information using suitably equipped computers. If,
               on the other hand, we consider the openness of multi-agent learning
               situations, this scenario lacks the aspects of interactivity,
               contextual openness and, above all, the multimodality of information
               objects, information processing and information exchange. This
               is where the chapter comes in. It describes Va.Si.Li-Lab as an
               instrument for multimodal measurement for studying and modeling
               multiple documents in the context of interactive learning in a
               multi-agent environment. To this end, the chapter places Va.Si.Li-Lab
               in the spectrum of evolutionary approaches that vary the combination
               of human and machine innovation and selection. It also combines
               the requirements of multimodal representational learning with
               various aspects of contextual plasticity to prepare Va.Si.Li-Lab
               as a system that can be used for experimental research. The chapter
               is conceptual in nature, designing a system of requirements using
               the example of Va.Si.Li-Lab to outline an experimental environment
               in which the study of Critical Online Reasoning (COR) as a group
               process becomes possible. Although the chapter illustrates some
               of these requirements with realistic data from the field of simulation-based
               learning, the focus is still conceptual rather than experimental,
               hypothesis-driven. That is, the chapter is concerned with the
               design of a technology for future research into COR processes.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_12},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_12}
}

@inbook{Konca:et:al:2024:a,
  author    = {Konca, Maxim and Mehler, Alexander and L{\"u}cking, Andy and Baumartz, Daniel},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Visualizing Domain-specific and Generic Critical Online Reasoning
               Related Structures of Online Texts: A Hybrid Approach},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {195--239},
  abstract  = {Besides ``traditional'' educational media, young professionals
               in higher education use the Internet to obtain information. To
               utilize their online research in professional contexts, they critically
               evaluate the information they access and its sources. One dimension
               of this evaluation is an assessment of the linguistic state of
               the online sources, either implicitly or explicitly. This computational
               educational linguistic study applies methods from computational
               linguistics to online sources visited by young professionals from
               three fields (law students, teacher trainees, and medicine student)
               and develops partly novel visualizations that allow to quickly
               discover similarities as well as differences between multi-heterogeneous
               Internet sources, that is, sources that exhibit various topics,
               genres, and textual structure, among others. The visualizations
               also allow a comparison of search behaviour between different
               professional fields. In this way, we found that (1) genre classification
               has a significant impact on reliability scores, (2) young professionals'
               search approaches vary by their professional field, and, (3) the
               best predictor of reliability is indeed the linguistic profile
               of an online source.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_10},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_10}
}

@book{Zlatkin-Troitschanskaia:et:al:2024,
  title     = {Students’, Graduates’ and Young Professionals’ Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  isbn      = {9783031695100},
  url       = {http://dx.doi.org/10.1007/978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0},
  publisher = {Springer Cham},
  year      = {2024},
  abstract  = {This book addresses the topic of online information for everyday
               personal and professional use by students, graduates, and young
               professionals. It focuses on the development of the job-related
               use of online information by young professionals in their practical
               phases of education (traineeship/practical year) in the domains
               of law, teaching, and medicine. The research conducted in this
               context investigates the general and domain-specific use of online
               resources in educational contexts and examines the effectiveness
               of an innovative digital training approach in enhancing skills
               required for the competent use of online information. For this
               purpose, the presented research uses a yet unprecedented approach
               of data triangulation, in which self-rated data, digitally and
               in vivo assessed response process data and expert ratings are
               integrated into a theoretically founded assessment framework and
               are examined from various interdisciplinary perspectives with
               different analysis methods. Overall, this work addresses key research
               questions related to the use of online information in practical
               tasks as well as to the impact of digital training. It provides
               in-depth multidisciplinary analyses of multimodal processes and
               performance data, allowing implications equally relevant for practitioners,
               policymakers, and researchers in the field of education.}
}

@bathesis{schrottenbacher:2024,
  author    = {Patrick Schrottenbacher},
  title     = {Identifying toxic behaviour in online games},
  institution = {Goethe University},
  pages     = {35},
  year      = {2024},
  url       = {https://publikationen.ub.uni-frankfurt.de/files/81676/Toxic_video_game_classification.pdf}
  repository = {https://github.com/TheBv/toxic-video-games-gnn}
}

@inproceedings{Henlein:Luecking:Mehler:2024,
  title     = {Virtually Restricting Modalities in Interactions: Va.Si.Li-Lab
               for Experimental Multimodal Research},
  author    = {Henlein, Alexander and L{\"u}cking, Andy and Mehler, Alexander},
  booktitle = {Proceedings of the 2nd International Symposium on Multimodal Communication
               (MMSYM 2024), Frankfurt, 25-27 September 2024},
  pages     = {96--97},
  year      = {2024},
  pdf       = {http://mmsym.org/wp-content/uploads/2024/09/BookOfAbstractsMMSYM2024-3.pdf}
}

@inproceedings{Luecking:Mehler:Henlein:2024,
  title     = {The Gesture–Prosody Link in Multimodal Grammar},
  author    = {L{\"u}cking, Andy and Mehler, Alexander and Henlein, Alexander},
  booktitle = {Proceedings of the 2nd International Symposium on Multimodal Communication
               (MMSYM 2024), Frankfurt, 25-27 September 2024},
  pages     = {128--129},
  year      = {2024},
  pdf       = {http://mmsym.org/wp-content/uploads/2024/09/BookOfAbstractsMMSYM2024-3.pdf}
}

@inproceedings{Ginzburg:Eliasmith:Luecking:2024-swann,
  title     = {Swann's name: {Towards} a Dialogical Brain Semantics},
  author    = {Ginzburg, Jonathan and Eliasmith, Chris and Lücking, Andy},
  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},
  url       = {https://www.semdial.org/anthology/papers/Z/Z24/Z24-3007/},
  pdf       = {http://semdial.org/anthology/Z24-Ginzburg_semdial_0007.pdf}
}

@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},
  url       = {https://www.semdial.org/anthology/papers/Z/Z24/Z24-4031/},
  pdf       = {http://semdial.org/anthology/Z24-Lucking_semdial_0031.pdf}
}

@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{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},
  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.},
  archiveprefix = {arXiv},
  eprint    = {2501.05018},
  url       = {https://arxiv.org/pdf/2501.05018},
  keywords  = {legal information retrieval, support vector regression, word embeddings, bagging ensemble}
}

@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}
}

@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{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{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.},
  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},
  pages     = {182--234},
  isbn      = {978-3-031-61066-0}
}

@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},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Poster.pdf},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Abstract.pdf},
  url       = {https://doi.org/10.5281/zenodo.13761079},
  pages     = {15--18},
  numpages  = {4}
}

@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{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{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{Gregori:et:al:2023-vicom,
  author    = {Gregori, Alina and Amici, Federica and Brilmayer, Ingmar and {\'{C}}wiek, Aleksandra
               and Fritzsche, Lennart and Fuchs, Susanne and Henlein, Alexander and Herbort, Oliver
               and K{\"u}gler, Frank and Lemanski, Jens and Liebal, Katja and L{\"u}cking, Andy
               and Mehler, Alexander and Nguyen, Kim Tien and Pouw, Wim and Prieto, Pilar
               and Rohrer, Patrick Louis and S{\'a}nchez-Ram{\'o}n, Paula G. and Schulte-R{\"u}ther, Martin
               and Schumacher, Petra B. and Schweinberger, Stefan R. and Struckmeier, Volker
               and Trettenbrein, Patrick C. and von Eiff, Celina I.},
  editor    = {Duffy, Vincent G.},
  title     = {A Roadmap for Technological Innovation in Multimodal Communication Research},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management},
  year      = {2023},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {402--438},
  abstract  = {Multimodal communication research focuses on how different means
               of signalling coordinate to communicate effectively. This line
               of research is traditionally influenced by fields such as cognitive
               and neuroscience, human-computer interaction, and linguistics.
               With new technologies becoming available in fields such as natural
               language processing and computer vision, the field can increasingly
               avail itself of new ways of analyzing and understanding multimodal
               communication. As a result, there is a general hope that multimodal
               research may be at the ``precipice of greatness'' due to technological
               advances in computer science and resulting extended empirical
               coverage. However, for this to come about there must be sufficient
               guidance on key (theoretical) needs of innovation in the field
               of multimodal communication. Absent such guidance, the research
               focus of computer scientists might increasingly diverge from crucial
               issues in multimodal communication. With this paper, we want to
               further promote interaction between these fields, which may enormously
               benefit both communities. The multimodal research community (represented
               here by a consortium of researchers from the Visual Communication
               [ViCom] Priority Programme) can engage in the innovation by clearly
               stating which technological tools are needed to make progress
               in the field of multimodal communication. In this article, we
               try to facilitate the establishment of a much needed common ground
               on feasible expectations (e.g., in terms of terminology and measures
               to be able to train machine learning algorithms) and to critically
               reflect possibly idle hopes for technical advances, informed by
               recent successes and challenges in computer science, social signal
               processing, and related domains.},
  isbn      = {978-3-031-35748-0},
  pdf       = {https://pure.mpg.de/rest/items/item_3511464_5/component/file_3520176/content}
}

@bathesis{boenisch:2023,
  author    = {Kevin B{\"o}nisch},
  title     = {Dialog generation using language models},
  institution = {Goethe University},
  pages     = {28},
  year      = {2023},
  url       = {https://publikationen.ub.uni-frankfurt.de/opus4/frontdoor/index/index/docId/79165},
  repository = {https://github.com/texttechnologylab/ROBERT}
}

@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{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.},
  keywords  = {duui}
}

@proceedings{SemDial:2023-marilogue,
  title     = {Proceedings of the 27th Workshop On the Semantics and Pragmatics of Dialogue},
  keywords  = {own,editor},
  year      = {2023},
  editor    = {Lücking, Andy and Mazzocconi, Chiara and Verdonik, Darinka},
  editor+an = {1=highlight},
  series    = {SemDial 2023 -- MariLogue},
  publisher = {University of Maribor},
  url       = {https://www.semdial.org/anthology/events/semdial-2023/}
}

@inproceedings{Ginzburg:Luecking:2023-wh,
  author    = {Ginzburg, Jonathan and Lücking, Andy},
  author+an = {2=highlight},
  keywords  = {own,conference},
  title     = {Referential Transparency and Inquisitivity},
  booktitle = {Proceedings of the 4th Workshop on Inquisitiveness Below and Beyond
               the Sentence Boundary},
  series    = {InqBnB4'23},
  pages     = {11-20},
  location  = {Nancy, France, hosted with IWCS 2023},
  year      = {2023},
  url       = {https://aclanthology.org/2023.inqbnb-1.2/},
  pdf       = {https://aclanthology.org/2023.inqbnb-1.2.pdf}
}

@inproceedings{Luecking:2023-rtt-annotation,
  author    = {Lücking, Andy},
  author+an = {1=highlight},
  keywords  = {own,conference},
  title     = {Towards Referential Transparent Annotations of Quantified Noun Phrases},
  booktitle = {Proceedings of the 2023 Joint ACL--ISO Workshop on Interoperable
               Semantic Annotation},
  series    = {ISA-19},
  pages     = {47-55},
  location  = {Nancy, France, hosted with IWCS 2023},
  year      = {2023},
  url       = {https://aclanthology.org/2023.isa-1.7/},
  pdf       = {https://aclanthology.org/2023.isa-1.7.pdf}
}

@inproceedings{Larsson:Cooper:Ginzburg:Luecking:2023-ttr-spa,
  author    = {Larsson, Staffan and Cooper, Robin and Ginzburg, Jonathan and Lücking, Andy},
  author+an = {4=highlight},
  keywords  = {own,conference},
  title     = {{TTR} at the {SPA}: {Relating} type-theoretical semantics to neural
               semantic pointers},
  booktitle = {Proceedings of Natural Logic Meets Machine Learning IV},
  series    = {NALOMA'23},
  location  = {Nancy, France, hosted with IWCS 2023},
  year      = {2023},
  url       = {https://aclanthology.org/2023.naloma-1.5/},
  pdf       = {https://aclanthology.org/2023.naloma-1.5.pdf}
}

@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{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{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{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}
}

@phdthesis{Henlein:2023,
  author    = {Alexander Henlein},
  title     = {Toward context-based text-to-3D scene generation},
  type      = {doctoralthesis},
  pages     = {199},
  school    = {Johann Wolfgang Goethe-Universität},
  doi       = {10.21248/gups.73448},
  year      = {2023},
  pdf       = {https://publikationen.ub.uni-frankfurt.de/files/73448/main.pdf}
}

@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{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}
}

@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}
}

@misc{Binder:et:al:2022,
  title     = {Full-Text Argumentation Mining on Scientific Publications},
  author    = {Arne Binder and Bhuvanesh Verma and Leonhard Hennig},
  year      = {2022},
  eprint    = {2210.13084},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url       = {https://arxiv.org/abs/2210.13084}
}

@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}
}

@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{Ginzburg:Luecking:2022:a,
  title     = {The Integrated Model of Memory: {A} Dialogical Perspective},
  author    = {Ginzburg, Jonathan and L{\"u}cking, Andy},
  booktitle = {Proceedings of SemDial 2022},
  series    = {SemDial 2022 -- DubDial},
  location  = {Dublin, Ireland},
  year      = {2022},
  editor    = {Gregoromichelaki, Eleni and Hough, Julian and Kelleher, John D.},
  pages     = {6-17},
  url       = {https://www.semdial.org/anthology/papers/Z/Z22/Z22-3004/},
  pdf       = {http://semdial.org/anthology/Z22-Ginzburg_semdial_0004.pdf}
}

@article{Luecking:Ginzburg:2022:b,
  title     = {Leading voices: {Dialogue} semantics, cognitive science, and the
               polyphonic structure of multimodal interaction},
  author    = {L{\"u}cking, Andy and Ginzburg, Jonathan},
  journal   = {Language and Cognition},
  year      = {2022},
  doi       = {10.1017/langcog.2022.30}
}

@inproceedings{Luecking:Ginzburg:2022:a,
  title     = {How to repair a slip of the tongue?},
  author    = {Lücking, Andy and Ginzburg, Jonathan},
  booktitle = {Proceedings of SemDial 2022},
  series    = {SemDial 2022 -- DubDial},
  location  = {Dublin, Ireland},
  year      = {2022},
  editor    = {Gregoromichelaki, Eleni and Hough, Julian and Kelleher, John D.},
  pages     = {35-46},
  url       = {https://www.semdial.org/anthology/papers/Z/Z22/Z22-3007/},
  pdf       = {http://semdial.org/anthology/Z22-Lücking_semdial_0007.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}
}

@article{Luecking:Ginzburg:2022,
  author    = {L{\"u}cking, Andy and Ginzburg, Jonathan},
  title     = {Referential transparency as the proper treatment of quantification},
  journal   = {Semantics and Pragmatics},
  year      = {2022},
  volume    = {15},
  eid       = {4},
  doi       = {10.3765/sp.15.4}
}

@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}
}

@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.}
}

@inproceedings{Abrami:Bagci:Hammerla:Mehler:2022,
  author    = {Abrami, Giuseppe and Bagci, Mevlüt and Hammerla, Leon and Mehler, Alexander},
  editor    = {Calzolari, Nicoletta and B\'echet, Fr\'ed\'eric and Blache, Philippe
               and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara
               and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H\'el\`ene
               and Odijk, Jan and Piperidis, Stelios},
  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{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 13th Language Resources and Evaluation Conference},
  series    = {LREC 2022},
  location  = {Marseille, France},
  year      = {2022},
  url       = {https://aclanthology.org/2022.lrec-1.505},
  pdf       = {https://aclanthology.org/2022.lrec-1.505.pdf}
}

@inproceedings{Ginzburg:Luecking:2021-clarifications,
  title     = {Requesting clarifications with speech and gestures},
  author    = {Ginzburg, Jonathan and L{\"u}cking, Andy},
  series    = {MMSR},
  year      = {2021},
  booktitle = {Proceedings of the 1st Workshop on Multimodal Semantic Representations},
  location  = {Groningen, Netherlands (Online)},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2021.mmsr-1.3},
  pdf       = {https://aclanthology.org/2021.mmsr-1.3.pdf},
  pages     = {21--31},
  abstract  = {In multimodal natural language interaction both speech and non-speech
               gestures are involved in the basic mechanism of grounding and
               repair. We discuss a couple of multimodal clarification requests
               and argue that gestures, as well as speech expressions, underlie
               comparable parallelism constraints. In order to make this precise,
               we slightly extend the formal dialogue framework KoS to cover
               also gestural counterparts of verbal locutionary propositions.}
}

@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{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}
}

@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}
}

@incollection{Luecking:Ginzburg:Cooper:2021,
  author    = {L\"{u}cking, Andy and Ginzburg, Jonathan and Cooper, Robin},
  title     = {Grammar in dialogue},
  chapter   = {26},
  pages     = {1155-1199},
  url       = {https://langsci-press.org/catalog/book/259},
  editor    = {M{\"u}ller, Stefan and Abeill{\'e}, Anne and Borsley, Robert D.
               and Koenig, Jean-Pierre},
  booktitle = {{Head Driven Phrase Structure Grammar: The handbook}},
  year      = {2021},
  series    = {Empirically Oriented Theoretical Morphology and
                  Syntax},
  number    = {9},
  address   = {Berlin},
  publisher = {Language Science Press},
  doi       = {10.5281/zenodo.5543318}
}

@incollection{Luecking:2021,
  author    = {L\"{u}cking, Andy},
  title     = {Gesture},
  pages     = {1201-1250},
  chapter   = {27},
  url       = {https://langsci-press.org/catalog/book/259},
  editor    = {M{\"u}ller, Stefan and Abeill{\'e}, Anne and Borsley, Robert D.
               and Koenig, Jean-Pierre},
  booktitle = {{Head Driven Phrase Structure Grammar: The handbook}},
  year      = {2021},
  series    = {Empirically Oriented Theoretical Morphology and
                  Syntax},
  number    = {9},
  address   = {Berlin},
  publisher = {Language Science Press},
  doi       = {10.5281/zenodo.5543318}
}

@inproceedings{Luecking:Ginzburg:2021:a,
  author    = {L{\"u}cking, Andy and Ginzburg, Jonathan},
  title     = {Saying and shaking `No'},
  booktitle = {{Proceedings of the 28th International Conference on Head-Driven
               Phrase Structure Grammar, Online (Frankfurt/Main)}},
  editor    = {M{\"u}ller, Stefan and Melnik, Nurit},
  issn      = {1535-1793},
  doi       = {10.21248/hpsg.2021.15},
  publisher = {University Library},
  address   = {Frankfurt/Main},
  pages     = {283--299},
  year      = {2021}
}

@inproceedings{Ginzburg:Luecking:2021:b,
  author    = {Ginzburg, Jonathan and L{\"u}cking, Andy},
  title     = {I thought pointing is rude: {A} dialogue-semantic analysis of
               pointing at the addressee},
  booktitle = {Proceedings of \textit{Sinn und Bedeutung 25}},
  series    = {SuB 25},
  year      = {2021},
  pages     = {276-291},
  editor    = {Grosz, Patrick and Mart{\'i}, Luisa and Pearson, Hazel and Sudo, Yasutada
               and Zobel, Sarah},
  note      = {Special Session: Gestures and Natural Language
                  Semantics},
  location  = {University College London (Online)},
  url       = {https://ojs.ub.uni-konstanz.de/sub/index.php/sub/article/view/937}
}

@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}
}

@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}
}

@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}
}

@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{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.}
}

@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}
}

@article{Paul:et:al:2020,
  title     = {Estimating electrification using multi-temporal DMSP/OLS night
               imagery as proxy measure of human well-being in India},
  author    = {Paul, Arati and Verma, Bhuvanesh and Chakraborty, Debasish},
  journal   = {Spatial Information Research},
  volume    = {28},
  issn      = {2366-3294},
  pages     = {469--473},
  year      = {2020},
  url       = {http://dx.doi.org/10.1007/s41324-019-00307-8},
  doi       = {10.1007/s41324-019-00307-8},
  publisher = {Springer}
}

@phdthesis{Uslu:2020,
  author    = {Tolga Uslu},
  title     = {Multi-document analysis : semantic analysis of large text corpora
               beyond topic modeling},
  pages     = {204},
  year      = {2020},
  url       = {http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56140},
  pdf       = {http://publikationen.ub.uni-frankfurt.de/files/56140/Dissertation_Tolga_Uslu.pdf}
}

@phdthesis{Hemati:2020,
  author    = {Wahed Hemati},
  title     = {TextImager-VSD : large scale verb sense disambiguation and named
               entity recognition in the context of TextImager},
  pages     = {174},
  year      = {2020},
  url       = {http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56089},
  pdf       = {http://publikationen.ub.uni-frankfurt.de/files/56089/dissertation_Wahed_Hemati.pdf}
}

@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{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}
}

@bathesis{Baumartz:2020,
  author    = {Baumartz, Daniel},
  title     = {{Automatic Topic Modeling in the Context of Digital Libraries:
               Mehrsprachige Korpus-basierte Erweiterung von text2ddc - eine
               experimentelle Studie}},
  year      = {2020},
  month     = {6},
  school    = {Johann Wolfgang Goethe-Universität, Institute of Computer
Science and Mathematics, Text Technology Lab},
  address   = {Frankfurt, Germany},
  url       = {https://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/56381},
  pdf       = {https://publikationen.ub.uni-frankfurt.de/files/56381/baumartz_bachelorarbeit_2020_pub.pdf}
}

@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}
}

@inproceedings{Ginzburg:Luecking:2020:a,
  author    = {Ginzburg, Jonathan and L{\"u}cking, Andy},
  title     = {On Laughter and Forgetting and Reconversing: {A} neurologically-inspired
               model of conversational context},
  booktitle = {Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue},
  series    = {SemDial/WatchDial},
  year      = {2020},
  location  = {Brandeis University, Waltham, New Jersey (Online)},
  url       = {https://www.semdial.org/anthology/papers/Z/Z20/Z20-3008/},
  pdf       = {http://semdial.org/anthology/Z20-Ginzburg_semdial_0008.pdf}
}

@inproceedings{Luecking:Ginzburg:2020,
  author    = {L{\"u}cking, Andy and Ginzburg, Jonathan},
  title     = {Towards the score of communication},
  booktitle = {Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue},
  series    = {SemDial/WatchDial},
  year      = {2020},
  location  = {Brandeis University, Waltham, New Jersey (Online)},
  url       = {https://www.semdial.org/anthology/papers/Z/Z20/Z20-3016/},
  pdf       = {http://semdial.org/anthology/Z20-Luecking_semdial_0016.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}
}

@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: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{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}
}

@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{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}
}

@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: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}
}

@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{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}
}

@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}
}

@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{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}
}

@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}
}

@incollection{Luecking:2019:a,
  author    = {L\"{u}cking, Andy},
  title     = {Dialogue semantics: {From} cognitive structures to positive and
               negative learning},
  year      = {2019},
  pages     = {197-205},
  publisher = {Springer Nature Switzerland AG},
  address   = {Cham, Switzerland},
  editor    = {Zlatkin-Troitschankskaia, Olga},
  booktitle = {Frontiers and Advances in Positive Learning in the Age of InformaTiOn (PLATO)},
  doi       = {10.1007/978-3-030-26578-6},
  url       = {https://link.springer.com/chapter/10.1007/978-3-030-26578-6_15}
}

@inproceedings{Luecking:Ginzburg:2019,
  author    = {L{\"u}cking, Andy and Ginzburg, Jonathan},
  title     = {Not few but all quantifiers can be negated: towards a referentially
               transparent semantics of quantified noun phrases},
  booktitle = {Proceedings of the Amsterdam Colloquium 2019},
  series    = {AC'19},
  location  = {University of Amsterdam},
  year      = {2019},
  pages     = {269-278},
  url       = {http://events.illc.uva.nl/AC/AC2019/},
  pdf       = {http://events.illc.uva.nl/AC/AC2019/uploaded_files/inlineitem/L_cking_and_Ginzburg_Not_few_but_all_quantifiers_ca.pdf}
}

@inproceedings{Schweter:Ahmed:2019,
  author    = {Stefan Schweter and Sajawel Ahmed},
  title     = {{Deep-EOS: General-Purpose Neural Networks for Sentence Boundary Detection}},
  booktitle = {Proceedings of the 15th Conference on Natural Language Processing (KONVENS)},
  location  = {Erlangen, Germany},
  year      = {2019}
}

@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.}
}

@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{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{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{Hoenen:2019dhd,
  author    = {Hoenen, Armin},
  title     = {{Rooting through Direction -- New and Old Approaches}},
  booktitle = {DHd 2019},
  url       = {https://zenodo.org/record/2596095#.XKtQb3Wg-vo},
  year      = {2019},
  month     = {jun}
}

@inproceedings{Hoenen:2019dgfs,
  author    = {Hoenen, Armin},
  title     = {{Interpreting and Post-Correcting the Minimum Spanning Tree}},
  booktitle = {DGfS 2019},
  url       = {http://www.dgfs2019.uni-bremen.de/abstracts/poster/Hoenen.pdf},
  year      = {2019}
}

@inproceedings{Hoenen:2019aiucd,
  author    = {Hoenen, Armin},
  title     = {{eLearning the URLCoFi – Digital Didactics for Humanists}},
  booktitle = {AIUCD 2019},
  url       = {http://aiucd2019.uniud.it/wp-content/uploads/2019/01/BoA-2019_PROVV.pdf},
  year      = {2019}
}

@inproceedings{Luecking:Cooper:Larsson:Ginzburg:2019,
  author    = {Lücking, Andy and Cooper, Robin and Larsson, Staffan and Ginzburg, Jonathan},
  title     = {Distribution is not enough -- Going {Firther}},
  booktitle = {Proceedings of Natural Language and Computer Science},
  maintitle = {The 13th International Conference on Computational
                  Semantics (IWCS 2019)},
  series    = {NLCS 6},
  location  = {Gothenburg, Sweden},
  month     = {May},
  year      = {2019},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2019/05/Distribution_is_not_enough.pdf}
}

@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{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.}
}

@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{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}
}

@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{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}
}

@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: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{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}
}

@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{HOENEN18.285,
  author    = {Armin Hoenen},
  title     = {{Multi Modal Distance - An Approach to Stemma Generation With Weighting}},
  booktitle = {Proceedings of the Eleventh International Conference on Language
               Resources and Evaluation (LREC 2018)},
  year      = {2018},
  month     = {May 7-12, 2018},
  address   = {Miyazaki, Japan},
  editor    = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri
               and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara
               and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno
               and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
  publisher = {European Language Resources Association (ELRA)},
  isbn      = {979-10-95546-00-9},
  url       = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/285.pdf},
  language  = {english}
}

@inproceedings{HOENEN18.314,
  author    = {Armin Hoenen},
  title     = {{From Manuscripts to Archetypes through Iterative Clustering}},
  booktitle = {Proceedings of the Eleventh International Conference on Language
               Resources and Evaluation (LREC 2018)},
  year      = {2018},
  month     = {May 7-12, 2018},
  address   = {Miyazaki, Japan},
  editor    = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri
               and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara
               and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno
               and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
  publisher = {European Language Resources Association (ELRA)},
  isbn      = {979-10-95546-00-9},
  url       = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/314.pdf},
  language  = {english}
}

@inproceedings{HOENEN18.349,
  author    = {Armin Hoenen and Niko Schenk},
  title     = {{Knowing the Author by the Company His Words Keep}},
  booktitle = {Proceedings of the Eleventh International Conference on Language
               Resources and Evaluation (LREC 2018)},
  year      = {2018},
  month     = {May 7-12, 2018},
  address   = {Miyazaki, Japan},
  editor    = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri
               and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara
               and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno
               and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
  publisher = {European Language Resources Association (ELRA)},
  isbn      = {979-10-95546-00-9},
  url       = {http://www.lrec-conf.org/proceedings/lrec2018/pdf/349.pdf},
  language  = {english}
}

@inproceedings{HOENEN18.9,
  author    = {Armin Hoenen},
  title     = {Attempts at Visualization of Etymological Information},
  booktitle = {Proceedings of the Eleventh International Conference on Language
               Resources and Evaluation (LREC 2018)},
  year      = {2018},
  month     = {may},
  date      = {7-12},
  location  = {Miyazaki, Japan},
  editor    = {Kernerman, Ilan and Krek, Simon},
  publisher = {European Language Resources Association (ELRA)},
  address   = {Paris, France},
  isbn      = {979-10-95546-28-3},
  language  = {english},
  url       = {http://lrec-conf.org/workshops/lrec2018/W33/pdf/book_of_proceedings.pdf}
}

@phdthesis{Hoenen2018,
  type      = {Dissertation},
  author    = {Armin Hoenen},
  title     = {Tools, evaluation and preprocessing for stemmatology},
  school    = {Goethe University Frankfurt},
  year      = {2018}
}

@inproceedings{Hoenen:Samushia:2018dhd,
  author    = {Hoenen, Armin and Samushia, Lela},
  title     = {{Principles Aiding in Reading Abbreviations in Old Georgian and Latin}},
  booktitle = {DHd 2018},
  url       = {http://dhd2018.uni-koeln.de/wp-content/uploads/boa-DHd2018-web-ISBN.pdf},
  year      = {2018}
}

@inproceedings{Hoenen:2018eadh,
  author    = {Hoenen, Armin},
  title     = {{Wikipedia Mention Graphs by Example}},
  booktitle = {EADH 2018},
  url       = {https://eadh2018.exordo.com/files/papers/37/final_draft/MentionGraphsEADH.pdf},
  year      = {2018}
}

@inproceedings{Hoenen:2018elexis,
  author    = {Hoenen, Armin},
  title     = {{Annotated Timelines and Stacked Area Plots for Visualization in Lexicography}},
  booktitle = {Elexis workshop at EADH 2018},
  url       = {https://lexdhai.insight-centre.org/Lex_DH__AI_2018_paper_2.pdf},
  year      = {2018}
}

@inbook{Hoenen:2018,
  author    = {Hoenen, Armin},
  title     = {Recurrence Analysis Function, a Dynamic Heatmap for the Visualization
               of Verse Text and Beyond},
  booktitle = {Visualisierung sprachlicher Daten: Visual Linguistics – Praxis – Tools},
  publisher = {Heidelberg University Press},
  abstract  = {The Recurrence Analysis Function (ReAF) is a cross-linguistic
               visualization tool for (historical) verse text, especially handwritten
               epics. It can also provide a general visualization of various
               aspects of prose text. It aims to enable intuitive understanding
               through explorative data analysis of historical, especially bardic-oral
               texts.1 The assumption behind this is that bardic/born-oral and
               non-bardic/born-written texts differ drastically in the way they
               employ repetition. The ReAF in its first implementation, as presented
               here, is a language-independent tool that permits the visual exploration
               of such structures. Firstly, general aspects and formal characteristics
               of oral verse text are characterized, before the main technical
               details and some additional applications of the ReAF are explained
               and illustrated.},
  year      = {2018},
  editors   = {Bubenhofer, Noah and Kupietz, Marc},
  place     = {Heidelberg},
  url       = {https://heiup.uni-heidelberg.de/reader/download/345/345-69-80909-2-10-20180411.pdf}
}

@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{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}
}

@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{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{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{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}
}

@incollection{Luecking:2018:a,
  author    = {Andy L\"{u}cking},
  title     = {Witness-loaded and Witness-free Demonstratives},
  booktitle = {Atypical Demonstratives},
  publisher = {De Gruyter},
  year      = {2018},
  editor    = {Marco Coniglio and Andrew Murphy and Eva Schlachter and Tonjes Veenstra},
  isbn      = {978-3-11-056029-9},
  url       = {https://www.degruyter.com/view/product/495228},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2020/05/Luecking-witness-loading-rg.pdf}
}

@inproceedings{Luecking:Ginzburg:2018,
  title     = {`Most people but not {Bill}': integrating sets, individuals and
               negation into a cognitively plausible account of noun phrase interpretation},
  booktitle = {Proceedings of Cognitive Structures: Linguistic, Philosophical
               and Psychological Perspectives},
  series    = {CoSt'18},
  author    = {L\"{u}cking, Andy and Ginzburg, Jonathan},
  year      = {2018}
}

@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{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}
}

@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{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}
}

@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{Abrami:Boden:Gleiss:2018,
  author    = {Abrami, Giuseppe and Boden, Gertrud and Glei\ss{}, Lisa},
  title     = {{World of the Khwe Bushmen: Accessing Khwe Cultural Heritage data
               by means of a digital ontology based on OWLnotator}},
  booktitle = {Proceedings of the Digital Humanities 2018},
  series    = {DH2018},
  location  = {Mexico City, Mexico},
  year      = {2018}
}

@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}
}

@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}
}

@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}
}

@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: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}
}

@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: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}
}

@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{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{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{Abrami:Mehler:2018,
  address   = {Miyazaki, Japan},
  author    = {Abrami, Giuseppe and Mehler, Alexander},
  booktitle = {Proceedings of the Eleventh International Conference on Language
               Resources and Evaluation ({LREC} 2018)},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher
               and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi
               and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion
               and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu},
  month     = {may},
  series    = {LREC 2018},
  keywords  = {UIMA},
  pdf       = {https://aclanthology.org/L18-1212.pdf},
  publisher = {European Language Resources Association (ELRA)},
  title     = {A {UIMA} Database Interface for Managing {NLP}-related Text Annotations},
  url       = {https://aclanthology.org/L18-1212},
  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}
}

@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}
}

@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       = {}
}

@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}
}

@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}
}

@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{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{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{Hoenen:Eger:Gehrke:2017,
  author    = {Hoenen, Armin and Eger, Steffen and Gehrke, Ralf},
  title     = {{How Many Stemmata with Root Degree k?}},
  booktitle = {Proceedings of the 15th Meeting on the Mathematics of Language},
  pages     = {11--21},
  publisher = {Association for Computational Linguistics},
  location  = {London, UK},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/How_Many_Stemmata_with_Root_Degree_k.pdf},
  url       = {http://aclweb.org/anthology/W17-3402},
  year      = {2017}
}

@inproceedings{Hoenen:2017:b,
  author    = {Hoenen, Armin},
  title     = {{Using Word Embeddings for Computing Distances Between Texts and
               for Authorship Attribution}},
  booktitle = {International Conference on Applications of Natural Language to
               Information Systems},
  pages     = {274--277},
  organization = {Springer},
  url       = {https://link.springer.com/chapter/10.1007/978-3-319-59569-6_33},
  year      = {2017}
}

@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}
}

@incollection{Hoenen:2017,
  author    = {Hoenen, Armin},
  title     = {{Beyond the tree – a theoretical model of contamination and a
               software to generate multilingual stemmata}},
  booktitle = {{Book of Abstracts of the annual conference of the AIUCD 2017, Sapienza, Rome}},
  publisher = {AIUCD},
  url       = {http://aiucd2017.aiucd.it/wp-content/uploads/2017/01/book-of-abstract-AIUCD-2017.pdf},
  year      = {2017}
}

@inproceedings{Luecking:2017:c,
  author    = {L\"{u}cking, Andy},
  title     = {Indexicals as Weak Descriptors},
  booktitle = {Proceedings of the 12th International Conference on Computational Semantics},
  series    = {IWCS 2017},
  address   = {Montpellier (France)},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/descriptive-indexicals_rev.pdf},
  year      = {2017}
}

@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}
}

@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{Luecking:2016:b,
  author    = {L\"{u}cking, Andy},
  title     = {Modeling Co-Verbal Gesture Perception in Type Theory with Records},
  booktitle = {Proceedings of the 2016 Federated Conference on Computer Science
               and Information Systems},
  editor    = {M. Ganzha and L. Maciaszek and M. Paprzycki},
  volume    = {8},
  series    = {Annals of Computer Science and Information Systems},
  pages     = {383-392},
  address   = {Gdansk, Poland},
  publisher = {IEEE},
  note      = {Best Paper Award},
  doi       = {10.15439/2016F83},
  pdf       = {http://annals-csis.org/Volume_8/pliks/83.pdf},
  url       = {http://annals-csis.org/Volume_8/drp/83.html},
  year      = {2016}
}

@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{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}
}

@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{Hoenen:2016DH,
  author    = {Hoenen, Armin},
  title     = {{Silva Portentosissima – Computer-Assisted Reflections on Bifurcativity
               in Stemmas}},
  booktitle = {Digital Humanities 2016: Conference Abstracts. Jagiellonian University
               \& Pedagogical University},
  series    = {DH 2016},
  pages     = {557-560},
  abstract  = {In 1928, the philologue Joseph Bédier explored contemporary stemmas
               and found them to contain a suspiciously large amount of bifurcations.
               In this paper, the argument is investigated that, with a large
               amount of lost manuscripts, the amount of bifurcations in the
               true stemmas would naturally be high because the probability for
               siblings to survive becomes very low is assessed via a computer
               simulation.},
  location  = {Kraków},
  url       = {http://dh2016.adho.org/abstracts/311},
  year      = {2016}
}

@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}
}

@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{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{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{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{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}
}

@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{Hoenen:2016x,
  author    = {Hoenen, Armin},
  title     = {{Wikipedia Titles As Noun Tag Predictors}},
  booktitle = {Proceedings of the 10th International Conference on Language Resources
               and Evaluation},
  series    = {LREC 2016},
  location  = {Portoro\v{z} (Slovenia)},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/18_Paper.pdf},
  year      = {2016}
}

@inproceedings{Hoenen:2016y,
  author    = {Hoenen, Armin},
  title     = {Das erste dynamische Stemma, Pionier des digitalen Zeitalters?},
  booktitle = {Accepted in the Proceedings of the Jahrestagung der Digital Humanities
               im deutschsprachigen Raum},
  url       = {http://www.dhd2016.de/abstracts/posters-060.html},
  year      = {2016}
}

@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{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}
}

@article{Hoenen:Samushia:2016,
  author    = {Armin Hoenen and Lela Samushia},
  title     = {{Gepi: An Epigraphic Corpus for Old Georgian and a Tool Sketch
               for Aiding Reconstruction}},
  journal   = {JLCL},
  volume    = {31},
  number    = {2},
  pages     = {25--38},
  year      = {2016}
}

@inproceedings{Hoenen:Mader:2015,
  author    = {Hoenen, Armin and Mader, Franziska},
  title     = {A New LMF Schema Application by Example of an Austrian Lexicon
               Applied to the Historical Corpus of the Writer Hugo von Hofmannsthal},
  booktitle = {Historical Corpora},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/HoenenMader2013-a-new-lmf-schema-application.pdf},
  website   = {http://www.narr-shop.de/historical-corpora.html},
  year      = {2015}
}

@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}
}

@phdthesis{Islam:2015,
  author    = {Mohammad Zahurul Islam},
  title     = {Multilingual text classification using information-theoretic features},
  pages     = {189},
  year      = {2015},
  pdf       = {http://publikationen.ub.uni-frankfurt.de/files/38157/thesis.pdf},
  abstract  = {The number of multilingual texts in the World Wide Web (WWW) is
               increasing dramatically and a multilingual economic zone like
               the European Union (EU) requires the availability of multilingual
               Natural Language Processing (NLP) tools. Due to a rapid development
               of NLP tools, many lexical, syntactic, semantic and other linguistic
               features have been used in different NLP applications. However,
               there are some situations where these features can not be used
               due the application type or unavailability of NLP resources for
               some of the languages. That is why an application that is intended
               to handle multilingual texts must have features that are not dependent
               on a particular language and specific linguistic tools. In this
               thesis, we will focus on two such applications: text readability
               and source and translation classification. In this thesis, we
               provide 18 features that are not only suitable for both applications,
               but are also language and linguistic tools independent. In order
               to build a readability classifier, we use texts from three different
               languages: English, German and Bangla. Our proposed features achieve
               a classification accuracy that is comparable with a classifier
               using 40 linguistic features. The readability classifier achieves
               a classification F-score of 74.21\% on the English Wikipedia corpus,
               an F-score of 75.47\% on the English textbook corpus, an F-score
               of 86.46\% on the Bangla textbook corpus and an F-score of 86.26\%
               on the German GEO/GEOLino corpus. We used more than two million
               sentence pairs from 21 European languages in order to build the
               source and translation classifier. The classifier using the same
               eighteen features achieves a classification accuracy of 86.63\%.
               We also used the same features to build a classifier that classifies
               translated texts based on their origin. The classifier achieves
               classification accuracy of 75\% for texts from 10 European languages.
               In this thesis, we also provide four different corpora, three
               for text readability analysis and one for corpus based translation
               studies.}
}

@article{Dundua:Hoenen:Samushia:2015,
  author    = {Dundua, Natia and Hoenen, Armin and Samushia, Lela},
  title     = {{A Parallel Corpus of the Old Georgian Gospel Manuscripts and
               their Stemmatology}},
  journal   = {The Georgian Journal for Language Logic Computation},
  volume    = {IV},
  pages     = {176-185},
  publisher = {CLLS, Tbilisi State University and Kurt G{\"o}del
                   Society},
  year      = {2015}
}

@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}
}

@inproceedings{Eger:2015_EMNLP,
  author    = {Eger, Steffen},
  title     = {Do we need bigram alignment models? On the effect of alignment
               quality on transduction accuracy in G2P},
  booktitle = {Proceedings of EMNLP},
  year      = {2015},
  pdf       = {https://www.aclweb.org/anthology/D15-1139}
}

@inproceedings{vorDerBrueck:Eger:2015,
  author    = {vor der Brück, Tim and Eger, Steffen},
  title     = {Deriving a primal form for the quadratic power kernel},
  booktitle = {Proceedings of the 38th German Conference on Artificial Intelligence ({KI})},
  year      = {2015}
}

@inproceedings{Eger:2015_Interspeech,
  author    = {Eger, Steffen},
  title     = {Improving G2P from Wiktionary and other (web) resources},
  booktitle = {Proceedings of Interspeech},
  pdf       = {https://pdfs.semanticscholar.org/bba8/30015d9cbfc40b975c25d0ec186280da6ab0.pdf},
  year      = {2015}
}

@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}
}

@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}
}

@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}
}

@inproceedings{Eger:2015_ACL,
  author    = {Eger, Steffen},
  title     = {Multiple Many-To-Many Sequence Alignment For Combining String-Valued
               Variables: A G2P Experiment},
  booktitle = {ACL},
  publisher = {Association for Computational Linguistics},
  year      = {2015}
}

@inproceedings{Eger:2015_SFCM,
  author    = {Eger, Steffen},
  title     = {Designing and comparing G2P-type lemmatizers for a morphology-rich language},
  publisher = {Fourth International Workshop on Systems and
                   Frameworks for Computational Morphology},
  year      = {2015}
}

@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}
}

@article{Eger:2015b,
  author    = {Eger, Steffen},
  title     = {Identities for Partial Bell Polynomials Derived from Identities
               for Weighted Integer Compositions.},
  journal   = {Aequationes Mathematicae},
  doi       = {10.1007/s00010-015-0338-2},
  year      = {2015}
}

@article{Eger:2015a,
  author    = {Eger, Steffen},
  title     = {Some Elementary Congruences for the Number of Weighted Integer Compositions.},
  journal   = {Journal of Integer Sequences (electronic only)},
  volume    = {18},
  number    = {4},
  pdf       = {https://cs.uwaterloo.ca/journals/JIS/VOL18/Eger/eger11.pdf},
  publisher = {School of Computer Science, University of Waterloo,
                   Waterloo, ON},
  year      = {2015}
}

@article{Luecking:Pfeiffer:Rieser:2015,
  author    = {Lücking, Andy and Pfeiffer, Thies and Rieser, Hannes},
  title     = {Pointing and Reference Reconsidered},
  journal   = {Journal of Pragmatics},
  volume    = {77},
  pages     = {56-79},
  abstract  = {Current semantic theory on indexical expressions claims that demonstratively
               used indexicals such as this lack a referent-determining meaning
               but instead rely on an accompanying demonstration act like a pointing
               gesture. While this view allows to set up a sound logic of demonstratives,
               the direct-referential role assigned to pointing gestures has
               never been scrutinized thoroughly in semantics or pragmatics.
               We investigate the semantics and pragmatics of co-verbal pointing
               from a foundational perspective combining experiments, statistical
               investigation, computer simulation and theoretical modeling techniques
               in a novel manner. We evaluate various referential hypotheses
               with a corpus of object identification games set up in experiments
               in which body movement tracking techniques have been extensively
               used to generate precise pointing measurements. Statistical investigation
               and computer simulations show that especially distal areas in
               the pointing domain falsify the semantic direct-referential hypotheses
               concerning pointing gestures. As an alternative, we propose that
               reference involving pointing rests on a default inference which
               we specify using the empirical data. These results raise numerous
               problems for classical semantics–pragmatics interfaces: we argue
               for pre-semantic pragmatics in order to account for inferential
               reference in addition to classical post-semantic Gricean pragmatics.},
  doi       = {10.1016/j.pragma.2014.12.013},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Luecking_Pfeiffer_Rieser_Pointing_and_Reference_Reconsiderd.pdf},
  website   = {http://www.sciencedirect.com/science/article/pii/S037821661500003X},
  year      = {2015}
}

@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{Hoenen:2015,
  author    = {Hoenen, Armin},
  title     = {Das artifizielle Manuskriptkorpus TASCFE},
  booktitle = {Accepted in the Proceedings of the Jahrestagung der Digital Humanities
               im deutschsprachigen Raum},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Hoenen_tascfeDH2015.pdf},
  year      = {2015}
}

@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}
}

@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}
}

@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{Hoenen:2015a,
  author    = {Hoenen, Armin},
  title     = {Lachmannian Archetype Reconstruction for Ancient Manuscript Corpora},
  booktitle = {Proceedings of the 2015 Conference of the North American Chapter
               of the Association for Computational Linguistics: Human Language
               Technologies (NAACL HLT)},
  note      = {Citation: Trovato is published in 2014 not in 2009.},
  abstract  = {Two goals are targeted by computer philology for ancient manuscript
               corpora: firstly, making an edition, that is roughly speaking
               one text version representing the whole corpus, which contains
               variety induced through copy errors and other processes and secondly,
               producing a stemma. A stemma is a graph-based visualization of
               the copy history with manuscripts as nodes and copy events as
               edges. Its root, the so-called archetype is the supposed original
               text or urtext from which all subsequent copies are made. Our
               main contribution is to present one of the first computational
               approaches to automatic archetype reconstruction and to introduce
               the first text-based evaluation for automatically produced archetypes.
               We compare a philologically generated archetype with one generated
               by bio-informatic software.},
  website   = {http://www.aclweb.org/anthology/N15-1127},
  year      = {2015}
}

@inproceedings{Hoenen:2015b,
  author    = {Hoenen, Armin},
  title     = {Simulating Misreading},
  booktitle = {Proceedings of the 20TH INTERNATIONAL CONFERENCE ON APPLICATIONS
               OF NATURAL LANGUAGE TO INFORMATION SYSTEMS (NLDB)},
  abstract  = {Physical misreading (as opposed to interpretational misreading)
               is an unnoticed substitution in silent reading. Especially for
               legally important documents or instruction manuals, this can lead
               to serious consequences. We present a prototype of an automatic
               highlighter targeting words which can most easily be misread in
               a given text using a dynamic orthographic neighbour concept. We
               propose measures of fit of a misread token based on Natural Language
               Processing and detect a list of short most easily misread tokens
               in the English language. We design a highlighting scheme for avoidance
               of misreading.},
  website   = {http://link.springer.com/chapter/10.1007/978-3-319-19581-0_34},
  year      = {2015}
}

@inproceedings{Abrami:Freiberg:Warner:2015,
  author    = {Abrami, Giuseppe and Freiberg, Michael and Warner, Paul},
  title     = {Managing and Annotating Historical Multimodal Corpora with the
               eHumanities Desktop - An outline of the current state of the LOEWE
               project Illustrations of Goethe s Faust},
  booktitle = {Historical Corpora},
  pages     = {353 - 363},
  abstract  = {Text corpora are structured sets of text segments that can be
               annotated or interrelated. Expanding on this, we can define a
               database of images as an iconographic multimodal corpus with annotated
               images and the relations between images as well as between images
               and texts. The Goethe-Museum in Frankfurt holds a significant
               collection of art work and texts relating to Goethe’s Faust from
               the early 19th century until the present. In this project we create
               a database containing digitized items from this collection, and
               extend a tool, the ImageDB in the eHumanities Desktop, to annotate
               and provide relations between resources. This article gives an
               overview of the project and provides some technical details. Furthermore
               we show newly implemented features, explain the challenge of creating
               an ontology on multimodal corpora and give a forecast for future
               work.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/AbramiFreibergWarner_HC_2012.pdf},
  website   = {http://www.narr-shop.de/historical-corpora.html},
  year      = {2015}
}

@incollection{Hoenen:2014plz,
  author    = {Hoenen, Armin},
  title     = {{Stemmatology, an interdisciplinary endeavour}},
  booktitle = {{Book of Abstracts zum DHd Workshop Informatik und die Digital Humanities}},
  publisher = {DHd},
  url       = {http://dhd-wp.hab.de/files/book_of_abstracts.pdf},
  year      = {2014}
}

@article{Chen:2014:a,
  author    = {Chen, Xinying},
  title     = {Language as a whole -- A new framework for linguistic knowledge
               integration: Comment on "Approaching human language with complex
               networks" by {Cong} and {Liu}},
  journal   = {Physics of Life Reviews},
  volume    = {11},
  number    = {4},
  pages     = {628-629},
  doi       = {10.1016/j.plrev.2014.07.011},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Language-as-a-whole-Chen.pdf},
  url       = {http://www.sciencedirect.com/science/article/pii/S1571064514001249},
  year      = {2014}
}

@article{Gong:Lam:Chen:Zhang:2014,
  author    = {Gong, Tao and Lam, Yau Wai and Chen, Xinying and Zhang, Menghan},
  title     = {Review: Evolutionary Linguistics in the Past Two Decades -- EVOLANG10:
               the 10th International Conference on Language Evolution},
  journal   = {Journal of Chinese Linguistics},
  volume    = {42},
  number    = {2},
  pages     = {499-530},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/JCL-EvolangReview.pdf},
  year      = {2014}
}

@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}
}

@article{Eger:2014:a,
  author    = {Eger, Steffen},
  title     = {A proof of the Mann-Shanks primality criterion conjecture for
               extended binomial coefficients},
  journal   = {Integers: The Electronic Journal of Combinatorial
                   Number Theory},
  volume    = {14},
  abstract  = {We show that the Mann-Shanks primality criterion holds for weighted
               extended binomial coefficients (which count the number of weighted
               integer compositions), not only for the ordinary binomial coefficients.},
  pdf       = {http://www.emis.de/journals/INTEGERS/papers/o60/o60.pdf},
  website   = {http://www.emis.de/journals/INTEGERS/vol14.html},
  year      = {2014}
}

@article{Eger:2014:b,
  author    = {Eger, Steffen},
  title     = {Stirling's approximation for central extended binomial coefficients.},
  journal   = {The American Mathematical Monthly},
  volume    = {121},
  number    = {4},
  pages     = {344-349},
  abstract  = {We derive asymptotic formulas for central extended binomial coefficients,
               which are generalizations of binomial coefficients, using the
               distribution of the sum of independent discrete uniform random
               variables with the Central Limit Theorem and a local limit variant.},
  website   = {http://www.jstor.org/stable/10.4169/amer.math.monthly.121.04.344},
  year      = {2014}
}

@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{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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@inproceedings{Hoenen:2014,
  author    = {Hoenen, Armin},
  title     = {Simulation of Scribal Letter Substitution},
  booktitle = {Analysis of Ancient and Medieval Texts and Manuscripts: Digital Approaches},
  editor    = {T.L Andrews and C.Macé},
  owner     = {hoenen},
  website   = {http://www.brepols.net/Pages/ShowProduct.aspx?prod_id=IS-9782503552682-1},
  year      = {2014}
}

@incollection{Sejane:Eger:2013,
  author    = {Sejane, Ineta and Eger, Steffen},
  title     = {Semantic typologies by means of network analysis of bilingual dictionaries},
  booktitle = {Approaches to Measuring Linguistic Differences},
  publisher = {De Gruyter},
  editor    = {Borin, Lars and Saxena, Anju},
  pages     = {447-474},
  bibtexkey = {eger-sejane_network-typologies2013},
  doi       = {10.1515/9783110305258.447},
  inlg      = {English [eng]},
  src       = {degruyter},
  srctrickle = {degruyter#/books/9783110305258/9783110305258.447/9783110305258.447.xml},
  url       = {http://www.degruyter.com/view/books/9783110305258/9783110305258.447/9783110305258.447.xml},
  year      = {2013}
}

@article{Eger:2013:a,
  author    = {Eger, Steffen},
  title     = {Sequence Segmentation by Enumeration: An Exploration.},
  journal   = {Prague Bull. Math. Linguistics},
  volume    = {100},
  pages     = {113-131},
  abstract  = {We investigate exhaustive enumeration and subsequent language
               model evaluation (E\&E approach) as an alternative to solving
               the sequence segmentation problem. We show that, under certain
               conditions (on string lengths and regarding a possibility to accurately
               estimate the number of segments), which are satisfied for important
               NLP applications, such as phonological segmentation, syllabification,
               and morphological segmentation, the E\&E approach is feasible
               and promises superior results than the standard sequence labeling
               approach to sequence segmentation.},
  pdf       = {http://ufal.mff.cuni.cz/pbml/100/art-eger.pdf},
  year      = {2013}
}

@article{Eger:2013:b,
  author    = {Eger, Steffen},
  title     = {A Contribution to the Theory of Word Length Distribution Based
               on a Stochastic Word Length Distribution Model.},
  journal   = {Journal of Quantitative Linguistics},
  volume    = {20},
  number    = {3},
  pages     = {252-265},
  abstract  = {We derive a stochastic word length distribution model based on
               the concept of compound distributions and show its relationships
               with and implications for Wimmer et al. ’s (1994) synergetic word
               length distribution model.},
  year      = {2013}
}

@article{Eger:2013:c,
  author    = {Eger, Steffen},
  title     = {Sequence alignment with arbitrary steps and further generalizations,
               with applications to alignments in linguistics.},
  journal   = {Information Sciences},
  volume    = {237},
  pages     = {287-304},
  abstract  = {We provide simple generalizations of the classical Needleman–Wunsch
               algorithm for aligning two sequences. First, we let both sequences
               be defined over arbitrary, potentially different alphabets. Secondly,
               we consider similarity functions between elements of both sequences
               with ranges in a semiring. Thirdly, instead of considering only
               ‘match’, ‘mismatch’ and ‘skip’ operations, we allow arbitrary
               non-negative alignment ‘steps’ S. Next, we present novel combinatorial
               formulas for the number of monotone alignments between two sequences
               for selected steps S. Finally, we illustrate sample applications
               in natural language processing that require larger steps than
               available in the original Needleman–Wunsch sequence alignment
               procedure such that our generalizations can be fruitfully adopted.},
  website   = {http://www.sciencedirect.com/science/article/pii/S0020025513001485},
  year      = {2013}
}

@article{Eger:2013:d,
  author    = {Eger, Steffen},
  title     = {Restricted weighted integer compositions and extended binomial coefficients.},
  journal   = {Journal of Integer Sequences (electronic only)},
  volume    = {16},
  number    = {1},
  abstract  = {We prove a simple relationship between extended binomial coefficients
               — natural extensions of the well-known binomial coefficients —
               and weighted restricted integer compositions. Moreover, wegiveaveryuseful
               interpretation ofextendedbinomial coefficients as representing
               distributions of sums of independent discrete random variables.
               We apply our results, e.g., to determine the distribution of the
               sum of k logarithmically distributed random variables, and to
               determining the distribution, specifying all moments, of the random
               variable whose values are part-products of random restricted integer
               compositions. Based on our findings and using the central limit
               theorem, we also give generalized Stirling formulae for central
               extended binomial coefficients. We enlarge the list of known properties
               of extended binomial coefficients.},
  issn      = {1530-7638},
  pdf       = {https://cs.uwaterloo.ca/journals/JIS/VOL16/Eger/eger6.pdf},
  publisher = {School of Computer Science, University of Waterloo,
                   Waterloo, ON},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.397.3745},
  year      = {2013}
}

@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}
}

@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}
}

@misc{Luecking:2013:c,
  author    = {Lücking, Andy},
  title     = {Theoretische Bausteine für einen semiotischen Ansatz zum Einsatz
               von Gestik in der Aphasietherapie},
  howpublished = {Talk at the BKL workshop 2013, Bochum},
  month     = {05},
  url       = {http://www.bkl-ev.de/bkl_workshop/archiv/workshop13_programm.php},
  year      = {2013}
}

@misc{Luecking:2013:d,
  author    = {Lücking, Andy},
  title     = {Eclectic Semantics for Non-Verbal Signs},
  howpublished = {Talk at the Conference on Investigating semantics:
                   Empirical and philosophical approaches, Bochum},
  month     = {10},
  url       = {http://www.ruhr-uni-bochum.de/phil-lang/investigating/index.html},
  year      = {2013}
}

@inproceedings{Luecking:2013:e,
  author    = {Lücking, Andy},
  title     = {Multimodal Propositions? From Semiotic to Semantic Considerations
               in the Case of Gestural Deictics},
  booktitle = {Poster Abstracts of the Proceedings of the 17th Workshop on the
               Semantics and Pragmatics of Dialogue},
  editor    = {Fernandez, Raquel and Isard, Amy},
  series    = {SemDial 2013},
  pages     = {221-223},
  address   = {Amsterdam},
  month     = {12},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/dialdam2013.pdf},
  year      = {2013}
}

@inproceedings{Islam:Hoenen:2013,
  author    = {Islam, Md. Zahurul and Hoenen, Armin},
  title     = {Source and Translation Classifiction using Most Frequent Words},
  booktitle = {Proceedings of the 6th International Joint Conference on Natural
               Language Processing (IJCNLP)},
  abstract  = {Recently, translation scholars have made some general claims about
               translation properties. Some of these are source language independent
               while others are not. Koppel and Ordan (2011) performed empirical
               studies to validate both types of properties using English source
               texts and other texts translated into English. Obviously, corpora
               of this sort, which focus on a single language, are not adequate
               for claiming universality of translation prop- erties. In this
               paper, we are validating both types of translation properties
               using original and translated texts from six European languages.},
  pdf       = {http://www.aclweb.org/anthology/I/I13/I13-1185.pdf},
  website   = {http://aclanthology.info/papers/source-and-translation-classification-using-most-frequent-words},
  year      = {2013}
}

@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}
}

@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}
}

@inproceedings{Luecking:2013:b,
  author    = {Lücking, Andy},
  title     = {Interfacing Speech and Co-Verbal Gesture: Exemplification},
  booktitle = {Proceedings of the 35th Annual Conference of the German Linguistic Society},
  series    = {DGfS 2013},
  pages     = {284-286},
  address   = {Potsdam, Germany},
  year      = {2013}
}

@book{Luecking:2013,
  author    = {Lücking, Andy},
  title     = {Ikonische Gesten. Grundzüge einer linguistischen Theorie},
  publisher = {De Gruyter},
  address   = {Berlin and Boston},
  note      = {Zugl. Diss. Univ. Bielefeld (2011)},
  abstract  = {Nicht-verbale Zeichen, insbesondere sprachbegleitende Gesten,
               spielen eine herausragende Rolle in der menschlichen Kommunikation.
               Um eine Analyse von Gestik innerhalb derjenigen Disziplinen, die
               sich mit der Erforschung und Modellierung von Dialogen besch{\"a}ftigen,
               zu ermöglichen, bedarf es einer entsprechenden linguistischen
               Rahmentheorie. „Ikonische Gesten“ bietet einen ersten zeichen-
               und wahrnehmungstheoretisch motivierten Rahmen an, in dem eine
               grammatische Analyse der Integration von Sprache und Gestik möglich
               ist. Ausgehend von einem Abriss semiotischer Zug{\"a}nge zu ikonischen
               Zeichen wird der vorherrschende {\"A}hnlichkeitsansatz unter Rückgriff
               auf Wahrnehmungstheorien zugunsten eines Exemplifikationsansatzes
               verworfen. Exemplifikation wird im Rahmen einer unifikationsbasierten
               Grammatik umgesetzt. Dort werden u.a. multimodale Wohlgeformtheit,
               Synchronie und multimodale Subkategorisierung als neue Gegenst{\"a}nde
               linguistischer Forschung eingeführt und im Rahmen einer integrativen
               Analyse von Sprache und Gestik modelliert.},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/ikonischeGesten.jpg},
  year      = {2013}
}

@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}
}

@inproceedings{Islam:Rahman:2013,
  author    = {Islam, Md. Zahurul and Rahman, Rashedur},
  title     = {English to Bangla Name Transliteration System (Abstract)},
  booktitle = {The 23rd Meeting of Computational Linguistics in the Netherlands (CLIN 2013)},
  abstract  = {Machine translation systems always struggle transliterating names
               and unknown words during the translation process. It becomes more
               problematic when the source and the target language use different
               scripts for writing. To handle this problem, transliteration systems
               are becoming popular as additional modules of the MT systems.
               In this abstract, we are presenting an English to Bangla name
               transliteration system that outperforms Google’s transliteration
               system. The transliteration system is the same as the phrase based
               statistical machine translation system, but it works on character
               level rather than on phrase level. The performance of a statistical
               system is directly correlated with the size of the training corpus.
               In this work, 2200 names are extracted from the Wikipedia cross
               lingual links and from Geonames . Also 3694 names are manually
               transliterated and added to the data. 4716 names are used for
               training, 590 for tuning and 588 names are used for testing. If
               we consider only the candidate transliterations, the system gives
               64.28\% accuracy. The performance increases to more than 90\%,
               if we consider only the top 5 transliterations. To compare with
               the Google’s English to Bangla transliteration system, a list
               of 100 names are randomly selected from the test data and translated
               by both systems. Our system gives 63\% accuracy where the Google’s
               transliteration system does not transliterate a single name correctly.
               We have found significant improvement in terms of BLUE and TER
               score when we add the transliteration module with an English to
               Bangla machine transliteration system.},
  owner     = {zahurul},
  timestamp = {2013.01.22},
  website   = {https://www.academia.edu/3955036/English_to_Bangla_Name_Transliteration_System},
  year      = {2013}
}

@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}
}

@article{Luecking:Bergmann:Hahn:Kopp:Rieser:2012,
  author    = {Lücking, Andy and Bergman, Kirsten and Hahn, Florian and Kopp, Stefan
               and Rieser, Hannes},
  title     = {Data-based Analysis of Speech and Gesture: The Bielefeld Speech
               and Gesture Alignment Corpus (SaGA) and its Applications},
  journal   = {Journal of Multimodal User Interfaces},
  volume    = {7},
  number    = {1-2},
  pages     = {5-18},
  abstract  = {Communicating face-to-face, interlocutors frequently produce multimodal
               meaning packages consisting of speech and accompanying gestures.
               We discuss a systematically annotated speech and gesture corpus
               consisting of 25 route-and-landmark-description dialogues, the
               Bielefeld Speech and Gesture Alignment corpus (SaGA), collected
               in experimental face-to-face settings. We first describe the primary
               and secondary data of the corpus and its reliability assessment.
               Then we go into some of the projects carried out using SaGA demonstrating
               the wide range of its usability: on the empirical side, there
               is work on gesture typology, individual and contextual parameters
               influencing gesture production and gestures’ functions for dialogue
               structure. Speech-gesture interfaces have been established extending
               unification-based grammars. In addition, the development of a
               computational model of speech-gesture alignment and its implementation
               constitutes a research line we focus on.},
  doi       = {10.1007/s12193-012-0106-8},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/MMUI-SaGA-revision2.pdf},
  website   = {http://www.springerlink.com/content/a547448u86h3116x/?MUD=MP},
  year      = {2013}
}

@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}
}

@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}
}

@phdthesis{Abramov:2012,
  author    = {Abramov, Olga},
  title     = {Network theory applied to linguistics: new advances in language
               classification and typology},
  school    = {Bielefeld University, Germany},
  abstract  = {This thesis bridges between two scientific fields -- linguistics
               and computer science -- in terms of Linguistic Networks. From
               the linguistic point of view we examine whether languages can
               be distinguished when looking at network topology of different
               linguistic networks. We deal with up to 17 languages and ask how
               far the methods of network theory reveal the peculiarities of
               single languages. We present and apply network models from different
               levels of linguistic representation: syntactic, phonological and
               morphological. The network models presented here allow to integrate
               various linguistic features at once, which enables a more abstract,
               holistic view at the particular language. From the point of view
               of computer science we elaborate the instrumentarium of network
               theory applying it to a new field. We study the expressiveness
               of different network features and their ability to characterize
               language structure. We evaluate the interplay of these features
               and their goodness in the task of classifying languages genealogically.
               Among others we compare network features related to: average degree,
               average geodesic distance, clustering, entropy-based indices,
               assortativity, centrality, compactness etc. We also propose some
               new indices that can serve as additional characteristics of networks.
               The results obtained show that network models succeed in classifying
               related languages, and allow to study language structure in general.
               The mathematical analysis of the particular network indices brings
               new insights into the nature of these indices and their potential
               when applied to different networks.},
  pdf       = {https://pub.uni-bielefeld.de/download/2538828/2542368},
  website   = {http://pub.uni-bielefeld.de/publication/2538828},
  year      = {2012}
}

@article{Hoenen:2012:a,
  author    = {Hoenen, Armin},
  title     = {Measuring Repetitiveness in Texts, a Preliminary Investigation},
  journal   = {Sprache und Datenverarbeitung. International Journal
                   for Language Data Processing},
  volume    = {36},
  number    = {2},
  pages     = {93-104},
  abstract  = {In this paper, a model is presented for the automatic measurement
               that can systematically describe the usage and function of the
               phenomenon of repetition in written text. The motivating hypothesis
               for this study is that the more repetitive a text is, the easier
               it is to memorize. Therefore, an automated measurement index can
               provide feedback to writers and for those who design texts that
               are often memorized including songs, holy texts, theatrical plays,
               and advertising slogans. The potential benefits of this kind of
               systematic feedback are numerous, the main one being that content
               creators would be able to employ a standard threshold of memorizability.
               This study explores multiple ways of implementing and calculating
               repetitiveness across levels of analysis (such as paragraph-level
               or sub-word level) genres (such as songs, holy texts, and other
               genres) and languages, integrating these into the a model for
               the automatic measurement of repetitiveness. The Avestan language
               and some of its idiosyncratic features are explored in order to
               illuminate how the proposed index is applied in the ranking of
               texts according to their repetitiveness.},
  website   = {http://www.linse.uni-due.de/jahrgang-36-2012/articles/measuring-repetitiveness-in-texts-a-preliminary-investigation.html},
  year      = {2012}
}

@article{Eger:2012:a,
  author    = {Eger, Steffen},
  title     = {The Combinatorics of String Alignments: Reconsidering the Problem.},
  journal   = {Journal of Quantitative Linguistics},
  volume    = {19},
  number    = {1},
  pages     = {32-53},
  abstract  = {In recent work, Covington discusses the number of alignments of
               two strings. Thereby, Covington defines an alignment as “a way
               of pairing up elements of two strings, optionally skipping some
               but preserving the order”. This definition has drawbacks as it
               excludes many relevant situations. In this work, we specify the
               notion of an alignment so that many linguistically interesting
               situations are covered. To this end, we define an alignment in
               an abstract manner as a set of pairs and then define three properties
               on such sets. Secondly, we specify the numbers of possibilities
               of aligning two strings in each case.},
  website   = {
                   http://www.tandfonline.com/doi/full/10.1080/09296174.2011.638792#tabModule},
  year      = {2012}
}

@inproceedings{Eger:2012:b,
  author    = {Eger, Steffen},
  title     = {S-Restricted Monotone Alignments: Algorithm, Search Space, and Applications},
  booktitle = {Proceedings of COLING 2012},
  pages     = {781-798},
  address   = {Mumbai, India},
  publisher = {The COLING 2012 Organizing Committee},
  abstract  = {We present a simple and straightforward alignment algorithm for
               monotone many-to-many alignments in grapheme-to-phoneme conversion
               and related fields such as morphology, and discuss a few noteworthy
               extensions. Moreover, we specify combinatorial formulas for monotone
               many-to-many alignments and decoding in G2P which indicate that
               exhaustive enumeration is generally possible, so that some limitations
               of our approach can easily be overcome. Finally, we present a
               decoding scheme, within the monotone many-to-many alignment paradigm,
               that relates the decoding problem to restricted integer compositions
               and that is, putatively, superior to alternatives suggested in
               the literatur},
  pdf       = {http://aclweb.org/anthology/C/C12/C12-1048.pdf},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.5941},
  year      = {2012}
}

@inproceedings{Eger:2012:c,
  author    = {Eger, Steffen},
  title     = {Lexical semantic typologies from bilingual corpora - A framework},
  booktitle = {SEM 2012: The First Joint Conference on Lexical and Computational
               Semantics -- Volume 1: Proceedings of the main conference and
               the shared task, and Volume 2: Proceedings of the Sixth International
               Workshop on Semantic Evaluation (SemEval 2012)},
  pages     = {90-94},
  address   = {Montreal, Canada},
  publisher = {Association for Computational Linguistics},
  abstract  = {We present a framework, based on Sejane and Eger (2012), for inducing
               lexical semantic typologies for groups of languages. Our framework
               rests on lexical semantic association networks derived from encoding,
               via bilingual corpora, each language in a common reference language,
               the tertium comparationis, so that distances between languages
               can easily be determined.},
  pdf       = {http://www.aclweb.org/anthology/S12-1015},
  website   = {http://dl.acm.org/citation.cfm?id=2387653},
  year      = {2012}
}

@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{Hoenen:Jügel:2012,
  author    = {Hoenen, Armin and Jügel, Thomas},
  editor    = {Armin Hoenen and Thomas Jügel},
  title     = {Altüberlieferte Sprachen als Gegenstand der Texttechnologie --
               Ancient Languages as the Object of Text Technology},
  publisher = {JLCL},
  volume    = {27},
  number    = {2},
  abstract  = {‘Avestan’ is the name of the ritual language of Zor oastrianism,
               which was the state religion of the Iranian empire in Achaemenid,
               Arsacid and Sasanid times, covering a time span of more than 1200
               years. [1] It is named after the ‘Avesta’, i.e., the collection
               of holy scriptures that form the basis of the religion which was
               allegedly founded by Zarathushtra, also known as Zoroaster, by
               about the beginning of the first millennium B.C. Together with
               Vedic Sanskrit, Avestan represents one of the most archaic witnesses
               of the Indo-Iranian branch of the Indo-European languages, which
               makes it especially interesting for historical-comparative linguistics.
               This is why the texts of the Avesta were among the first objects
               of electronic corpus building that were undertaken in the framework
               of Indo-European studies, leading to the establishment of the
               TITUS database (‘Thesaurus indogermanischer Text- u nd Sprachmaterialien’).
               [2] Today, the complete Avestan corpus is available, together
               with elaborate search functions [3] and an extended version of
               the subcorpus of the so-called ‘Yasna’, which covers a great deal
               of the attestation of variant readings. [4] Right from the beginning
               of their computational work concerning the Avesta, the compilers
               [5] had to cope with the fact that the texts contained in it have
               been transmitted in a special script written from right to left,
               which was also used for printing them in the scholarly editions
               used until today. [6] It goes without saying that there was no
               way in the middle of the 1980s to encode the Avestan scriptures
               exactly as they are found in the manuscripts. Instead, we had
               to rely upon transcriptional devices that were dictated by the
               restrictions of character encoding as provided by the computer
               systems used. As the problems we had to face in this respect and
               the solutions we could apply are typical for the development of
               computational work on ancient languages, it seems worthwhile to
               sketch them out here.},
  image     = {https://www.texttechnologylab.org/wp-content/uploads/2015/09/AltueberlieferteSprachen-300-20.png},
  issn      = {2190-6858},
  pdf       = {http://www.jlcl.org/2012_Heft2/H2012-2.pdf},
  year      = {2012}
}

@book{vor:der:Brueck:2012:a,
  author    = {vor der Brück, Tim},
  title     = {Wissensakquisition mithilfe maschineller Lernverfahren auf tiefen
               semantischen Repr{\"a}sentationen},
  publisher = {Springer},
  address   = {Heidelberg, Germany},
  abstract  = {Eine gro{\ss}e Wissensbasis ist eine Voraussetzung für eine Vielzahl
               von Anwendungen im Bereich der automatischen Sprachverarbeitung,
               wie Frage-Antwort- oder Information-Retrieval-Systeme. Ein Mensch
               hat sich das erforderliche Wissen, um Informationen zu suchen
               oder Fragen zu beantworten, im Laufe seines Lebens angeeignet.
               Einem Computer muss dieses Wissen explizit mitgeteilt werden.
               Tim vor der Brück beschreibt einen Ansatz, wie ein Computer dieses
               Wissen {\"a}hnlich wie ein Mensch durch die Lektüre von Texten
               erwerben kann. Dabei kommen Methoden der Logik und des maschinellen
               Lernens zum Einsatz.},
  school    = {FernUniversit{\"a}t in Hagen},
  year      = {2012}
}

@inproceedings{vor:der:Brueck:Wang:2012,
  author    = {vor der Brück, Tim and Wang, Yu-Fang},
  title     = {Synonymy Extraction from Semantic Networks Using String and Graph Kernel Methods},
  booktitle = {Proceedings of the 20th European Conference on Artificial Intelligence (ECAI)},
  pages     = {822--827},
  address   = {Montpellier, France},
  abstract  = {Synonyms are a highly relevant information source for natural
               language processing. Automatic synonym extraction methods have
               in common that they are either applied on the surface representation
               of the text or on a syntactical structure derived from it. In
               this paper, however, we present a semantic synonym extraction
               approach that operates directly on semantic networks (SNs), which
               were derived from text by a deep syntactico-semantic analysis.
               Synonymy hypotheses are extracted from the SNs by graph matching.
               These hypotheses are then validated by a support vector machine
               (SVM) employing a combined graph and string kernel. Our method
               was compared to several other approaches and the evaluation has
               shown that our results are considerably superior},
  pdf       = {http://www.vdb1.de/papers/ECAI_535.pdf},
  website   = {http://ebooks.iospress.nl/publication/7076},
  year      = {2012}
}

@incollection{vor:der:Brueck:2012:b,
  author    = {vor der Brück, Tim},
  title     = {Hyponym Extraction Employing a Weighted Graph Kernel},
  booktitle = {Statistical and Machine Learning Approaches for Network Analysis},
  publisher = {Wiley},
  editor    = {Matthias Dehmer and Subhash C. Basak},
  address   = {Hoboken, New Jersey},
  year      = {2012}
}

@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}
}

@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{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}
}

@inproceedings{Luecking:2012,
  author    = {Lücking, Andy},
  title     = {Towards a Conceptual, Unification-based Speech-Gesture Interface},
  booktitle = {Proceedings of the International Workshop on Formal and Computational
               Approaches to Multimodal Communication under the auspices of ESSLLI
               2012, Opole, Poland, 6-10 August},
  editor    = {Gianluca Giorgolo and Katya Alahverdzhieva},
  abstract  = {A framework for grounding the semantics of co-verbal iconic gestures
               is presented. A resemblance account to iconicity is discarded
               in favor of an exemplification approach. It is sketched how exemplification
               can be captured within a unification-based grammar that provides
               a conceptual interface. Gestures modeled as vector sequences are
               the exemplificational base. Some hypotheses that follow from the
               general account are pointed at and remaining challenges are discussed.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/FoCoMoC2012-1.pdf},
  year      = {2012}
}

@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{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: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}
}

@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}
}

@incollection{Luecking:Ptock:Bergmann:2012,
  author    = {Lücking, Andy and Ptock, Sebastian and Bergmann, Kirsten},
  title     = {Assessing Agreement on Segmentations by Means of Staccato, the
               Segmentation Agreement Calculator according to Thomann},
  booktitle = {Gesture and Sign Language in Human-Computer Interaction and Embodied
               Communication},
  publisher = {Springer},
  editor    = {Eleni Efthimiou and Georgios Kouroupetroglou and Stavroula-Evita Fotina},
  volume    = {7206},
  series    = {Lecture Notes in Artificial Intelligence},
  pages     = {129-138},
  address   = {Berlin and Heidelberg},
  abstract  = {Staccato, the Segmentation Agreement Calculator According to Thomann
               , is a software tool for assessing the degree of agreement of
               multiple segmentations of some time-related data (e.g., gesture
               phases or sign language constituents). The software implements
               an assessment procedure developed by Bruno Thomann and will be
               made publicly available. The article discusses the rationale of
               the agreement assessment procedure and points at future extensions
               of Staccato.},
  booksubtitle = {9th International Gesture Workshop, GW 2011, Athens,
                   Greece, May 2011, Revised Selected Papers},
  website   = {http://link.springer.com/chapter/10.1007/978-3-642-34182-3_12},
  year      = {2012}
}

@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}
}

@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}
}

@incollection{Luecking:Pfeiffer:2012,
  author    = {Lücking, Andy and Pfeiffer, Thies},
  title     = {Framing Multimodal Technical Communication. With Focal Points
               in Speech-Gesture-Integration and Gaze Recognition},
  booktitle = {Handbook of Technical Communication},
  publisher = {De Gruyter Mouton},
  editor    = {Alexander Mehler and Laurent Romary and Dafydd Gibbon},
  volume    = {8},
  series    = {Handbooks of Applied Linguistics},
  chapter   = {18},
  pages     = {591-644},
  website   = {http://www.degruyter.com/view/books/9783110224948/9783110224948.591/9783110224948.591.xml},
  year      = {2012}
}

@incollection{Kubina:Abramov:Luecking:2012,
  author    = {Kubina, Petra and Abramov, Olga and Lücking, Andy},
  title     = {Barrier-free Communication},
  booktitle = {Handbook of Technical Communication},
  publisher = {De Gruyter Mouton},
  editor    = {Alexander Mehler and Laurent Romary},
  volume    = {8},
  series    = {Handbooks of Applied Linguistics},
  chapter   = {19},
  pages     = {645-706},
  address   = {Berlin and Boston},
  editora   = {Dafydd Gibbon},
  editoratype = {collaborator},
  website   = {http://www.degruyter.com/view/books/9783110224948/9783110224948.645/9783110224948.645.xml},
  year      = {2012}
}

@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{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}
}

@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}
}

@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}
}

@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}
}

@inproceedings{Luecking:Ptock:Bergmann:2011,
  author    = {Lücking, Andy and Ptock, Sebastian and Bergmann, Kirsten},
  title     = {Staccato: Segmentation Agreement Calculator},
  booktitle = {Gesture in Embodied Communication and Human-Computer Interaction.
               Proceedings of the 9th International Gesture Workshop},
  editor    = {Eleni Efthimiou and Georgios Kouroupetroglou},
  series    = {GW 2011},
  pages     = {50--53},
  address   = {Athens, Greece},
  publisher = {National and Kapodistrian University of Athens},
  month     = {5},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/LueckingEA_final.pdf},
  year      = {2011}
}

@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}
}

@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}
}

@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{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{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{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}
}

@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{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{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}
}

@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{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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@book{Waltinger:2011,
  author    = {Waltinger, Ulli},
  title     = {On Social Semantics in Information Retrieval},
  publisher = {Südwestdeutscher Verlag für Hochschulschriften},
  address   = {Saarbrücken},
  note      = {Zugl. Diss Univ. Bielefeld (2010)},
  abstract  = {In this thesis we analyze the performance of social semantics
               in textual information retrieval. By means of collaboratively
               constructed knowledge derived from web-based social networks,
               inducing both common-sense and domain-specific knowledge as constructed
               by a multitude of users, we will establish an improvement in performance
               of selected tasks within different areas of information retrieval.
               This work connects the concepts and the methods of social networks
               and the semantic web to support the analysis of a social semantic
               web that combines human intelligence with machine learning and
               natural language processing. In this context, social networks,
               as instances of the social web, are capable in delivering social
               network data and document collections on a tremendous scale, inducing
               thematic dynamics that cannot be achieved by traditional expert
               resources. The question of an automatic conversion, annotation
               and processing, however, is central to the debate of the benefits
               of the social semantic web. Which kind of technologies and methods
               are available, adequate and contribute to the processing of this
               rapidly rising flood of information and at the same time being
               capable of using the wealth of information in this large, but
               more importantly decentralized internet. The present work researches
               the performance of social semantic-induced categorization by means
               of different document models. We will shed light on the question,
               to which level social networks and social ontologies contribute
               to selected areas within the information retrieval area, such
               as automatically determining term and text associations, identifying
               topics, text and web genre categorization, and also the domain
               of sentiment analysis. We will show in extensive evaluations,
               comparing the classical apparatus of text categorization -- Vector
               Space Model, Latent Semantic Analysis and Support Vector Maschine
               -- that significant improvements can be obtained by considering
               the collaborative knowledge derived from the social web.},
  pdf       = {https://pub.uni-bielefeld.de/download/2302025/2302028},
  website   = {http://www.ulliwaltinger.de/on-social-semantics-in-information-retrieval/},
  year      = {2011}
}

@inproceedings{Doebenhenisch:Abrami:Pfaff:Struwe:2011,
  author    = {Doeben-Henisch, Gerd and Abrami, Giuseppe and Pfaff, Marcus and Struwe, Marvin},
  title     = {Conscious learning semiotics systems to assist human persons (CLS2H)},
  booktitle = {AFRICON, 2011},
  volume    = {},
  number    = {},
  pages     = {1 -7},
  abstract  = {Challenged by the growing societal demand for Ambient Assistive
               Living (AAL) technologies, we are dedicated to develop intelligent
               technical devices which are able to communicate with human persons
               in a truly human-like manner. The core of the project is a simulation
               environment which enables the development of conscious learning
               semiotic agents which will be able to assist human persons in
               their daily life. We are reporting first results and future perspectives.},
  doi       = {10.1109/AFRCON.2011.6072043},
  issn      = {2153-0025},
  keywords  = {ambient assistive living;conscious learning semiotic
                   agents;conscious learning semiotics systems;human
                   persons;intelligent technical devices;simulation
                   environment;learning (artificial
                   intelligence);multi-agent systems;},
  month     = {sept.},
  pdf       = {http://www.doeben-henisch.de/gdhnp/csg/africon2011.pdf},
  website   = {http://www.researchgate.net/publication/261451874_Conscious_Learning_Semiotics_Systems_to_Assist_Human_Persons_(CLS(2)H)},
  year      = {2011}
}

@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}
}

@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}
}

@inproceedings{Dong:vor:der:Brueck:2011,
  author    = {Dong, Tiansi and vor der Brück, Tim},
  title     = {Qualitative Spatial Knowledge Acquisition Based on the Connection Relation},
  booktitle = {Proceedings of the 3rd International Conference on Advanced Cognitive
               Technologies and Applications (COGNITIVE)},
  editor    = {Terry Bossomaier and Pascal Lorenz},
  pages     = {70--75},
  address   = {Rome, Italy},
  abstract  = {Research in cognitive psychology shows that the connection relation
               is the primitive spatial relation. This paper proposes a novel
               spatial knowledge representation of indoor environments based
               on the connection relation, and demonstrates how deictic orientation
               relations can be acquired from a map, which is constructed purely
               on connection relations between extended objects. Without loss
               of generality, we restrict indoor environments to be constructed
               by a set of rectangles, each representing either a room or a corridor.
               The term fiat cell is coined to represent a subjective partition
               along a corridor. Spatial knowledge includes rectangles, sides
               information of rectangles, connection relations among rectangles,
               and fiat cells of rectangles. Efficient algorithms are given for
               identifying one shortest path between two locations, transforming
               paths into fiat paths, and acquiring deictic orientations.},
  pdf       = {http://www.thinkmind.org/download.php?articleid=cognitive_2011_3_40_40123},
  website   = {http://www.thinkmind.org/index.php?view=article&articleid=cognitive_2011_3_40_40123},
  year      = {2011}
}

@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}
}

@inproceedings{Ries:Luecking:2011,
  author    = {Ries, Veronika and Lücking, Andy},
  booktitle = {Multilingual Resources and Multilingual Applications: Proceedings
               of the German Society for Computational Linguistics 2011},
  year      = {2011},
  pages     = {207--210},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/Ries_Luecking.pdf},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/SoSaBiEC-poster.pdf}
}

@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{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}
}

@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}
}

@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}
}

@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}
}

@inproceedings{vor:der:Brueck:Stenzhorn:2010,
  author    = {vor der Brück, Tim and Stenzhorn, Holger},
  title     = {Logical Ontology Validation Using an Automatic Theorem Prover},
  booktitle = {Proceedings of the 19th European Conference on Artificial Intelligence (ECAI)},
  pages     = {491--496},
  address   = {Lisbon, Portugal},
  abstract  = {Ontologies are utilized for a wide range of tasks, like information
               retrieval/extraction or text generation, and in a multitude of
               domains, such as biology, medicine or business and commerce. To
               be actually usable in such real-world scenarios, ontologies usually
               have to encompass a large number of factual statements. However,
               with increasing size, it becomes very diffcult to ensure their
               complete correctness. This is particularly true in the case when
               an ontology is not hand-crafted but constructed (semi)automatically
               through text mining, for example. As a consequence, when inference
               mechanisms are applied on these ontologies, even minimal inconsistencies
               of tentimes lead to serious errors and are hard to trace back
               and find. This paper addresses this issue and describes a method
               to validate ontologies using an automatic theorem prover and MultiNet
               axioms. This logic-based approach allows to detect many inconsistencies,
               which are diffcult or even impossible to identify through statistical
               methods or by manual investigation in reasonable time. To make
               this approach accessible for ontology developers, a graphical
               user interface is provided that highlights erroneous axioms directly
               in the ontology for quicker fixing.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/ECAI-216.pdf},
  year      = {2010}
}

@article{vor:der:Brueck:2010,
  author    = {vor der Brück, Tim},
  title     = {Hypernymy Extraction Using a Semantic Network Representation},
  journal   = {International Journal of Computational Linguistics and
                   Applications},
  volume    = {1},
  number    = {1},
  pages     = {105--119},
  abstract  = {There are several approaches to detect hypernymy relations from
               texts by text mining. Usually these approaches are based on supervised
               learning and in a first step are extracting several patterns.
               These patterns are then applied to previously unseen texts and
               used to recognize hypernym/hyponym pairs. Normally these approaches
               are only based on a surface representation or a syntactical tree
               structure, i.e., constituency or dependency trees derived by a
               syntactical parser. In this work, however, we present an approach
               that operates directly on a semantic network (SN), which is generated
               by a deep syntactico-semantic analysis. Hyponym/hypernym pairs
               are then extracted by the application of graph matching. This
               algorithm is combined with a shallow approach enriched with semantic
               information.},
  pdf       = {http://www.gelbukh.com/ijcla/2010-1-2/Hypernymy
                   Extraction Using.pdf},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.358.533},
  year      = {2010}
}

@inproceedings{vor:der:Brueck:2010:a,
  author    = {vor der Brück, Tim},
  title     = {Learning Deep Semantic Patterns for Hypernymy Extraction Following
               the Minimum Description Length Principle},
  booktitle = {Proceedings of the 29th International Conference on Lexis and Grammar (LGC)},
  pages     = {39--49},
  address   = {Belgrade, Serbia},
  abstract  = {Current approaches of hypernymy acquisition are mostly based on
               syntactic or surface representations and extract hypernymy relations
               between surface word forms and not word readings. In this paper
               we present a purely semantic approach for hypernymy extraction
               based on semantic networks (SNs). This approach employs a set
               of patterns sub0 (a1,a2) <-- premise where the premise part of
               a pattern is given by a SN. Furthermore this paper describes how
               the patterns can be derived by relational statistical learning
               following the Minimum Description Length principle (MDL). The
               evaluation demonstrates the usefulness of the learned patterns
               and also of the entire hypernymy extraction system.},
  year      = {2010}
}

@inproceedings{vor:der:Brueck:2010:b,
  author    = {vor der Brück, Tim},
  title     = {Learning Semantic Network Patterns for Hypernymy Extraction},
  booktitle = {Proceedings of the 6th Workshop on Ontologies and Lexical Resources (OntoLex)},
  pages     = {38--47},
  address   = {Beijing, China},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/ontolex_brueck_13_2010.pdf},
  website   = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.358.533},
  year      = {2010}
}

@inproceedings{vor:der:Brueck:Hartrumpf:Eichhorn:2010:a,
  author    = {Hartrumpf, Sven and vor der Brück, Tim and Eichhorn, Christian},
  title     = {Detecting Duplicates with Shallow and Parser-based Methods},
  booktitle = {Proceedings of the 6th International Conference on Natural Language
               Processing and Knowledge Engineering (NLPKE)},
  pages     = {142--149},
  address   = {Beijing, China},
  abstract  = {Identifying duplicate texts is important in many areas like plagiarism
               detection, information retrieval, text summarization, and question
               answering. Current approaches are mostly surface-oriented (or
               use only shallow syntactic representations) and see each text
               only as a token list. In this work however, we describe a deep,
               semantically oriented method based on semantic networks which
               are derived by a syntactico-semantic parser. Semantically identical
               or similar semantic networks for each sentence of a given base
               text are efficiently retrieved by using a specialized semantic
               network index. In order to detect many kinds of paraphrases the
               current base semantic network is varied by applying inferences:
               lexico-semantic relations, relation axioms, and meaning postulates.
               Some important phenomena occurring in difficult-to-detect duplicates
               are discussed. The deep approach profits from background knowledge,
               whose acquisition from corpora like Wikipedia is explained briefly.
               This deep duplicate recognizer is combined with two shallow duplicate
               recognizers in order to guarantee high recall for texts which
               are not fully parsable. The evaluation shows that the combined
               approach preserves recall and increases precision considerably,
               in comparison to traditional shallow methods. For the evaluation,
               a standard corpus of German plagiarisms was extended by four diverse
               components with an emphasis on duplicates (and not just plagiarisms),
               e.g., news feed articles from different web sources and two translations
               of the same short story.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/semdupl-ieee.pdf},
  website   = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5587838&abstractAccess=no&userType=inst},
  year      = {2010}
}

@inproceedings{vor:der:Brueck:Hartrumpf:Eichhorn:2010:b,
  author    = {Hartrumpf, Sven and vor der Brück, Tim and Eichhorn, Christian},
  title     = {Semantic Duplicate Identification with Parsing and Machine Learning},
  booktitle = {Proceedings of the 13th International Conference on Text, Speech
               and Dialogue (TSD 2010)},
  editor    = {Petr Sojka and Aleš Horák and Ivan Kopeček and Karel Pala},
  volume    = {6231},
  series    = {Lecture Notes in Artificial Intelligence},
  pages     = {84--92},
  address   = {Brno, Czech Republic},
  abstract  = {Identifying duplicate texts is important in many areas like plagiarism
               detection, information retrieval, text summarization, and question
               answering. Current approaches are mostly surface-oriented (or
               use only shallow syntactic representations) and see each text
               only as a token list. In this work however, we describe a deep,
               semantically oriented method based on semantic networks which
               are derived by a syntacticosemantic parser. Semantically identical
               or similar semantic networks for each sentence of a given base
               text are efficiently retrieved by using a specialized index. In
               order to detect many kinds of paraphrases the semantic networks
               of a candidate text are varied by applying inferences: lexico-
               semantic relations, relation axioms, and meaning postulates. Important
               phenomena occurring in difficult duplicates are discussed. The
               deep approach profits from background knowledge, whose acquisition
               from corpora is explained briefly. The deep duplicate recognizer
               is combined with two shallow duplicate recognizers in order to
               guarantee a high recall for texts which are not fully parsable.
               The evaluation shows that the combined approach preserves recall
               and increases precision considerably in comparison to traditional
               shallow methods.},
  month     = {September},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/semdupl-paper.pdf},
  website   = {http://link.springer.com/chapter/10.1007/978-3-642-15760-8_12},
  year      = {2010}
}

@article{vor:der:Brueck:Helbig:2010:b,
  author    = {vor der Brück, Tim and Helbig, Hermann},
  title     = {Retrieving Meronyms from Texts Using An Automated Theorem Prover},
  journal   = {Journal for Language Technology and Computational
                   Linguistics (JLCL)},
  volume    = {25},
  number    = {1},
  pages     = {57--81},
  abstract  = {In this paper we present a truly semantic-oriented approach for
               meronymy relation extraction. It directly operates, instead of
               syntactic trees or surface representations, on semantic networks
               (SNs). These SNs are derived from texts (in our case, the German
               Wikip edia) by a deep linguistic syntactico-semantic analysis.
               The extraction of meronym/holonym pairs is carried out by using,
               among other components, an automated theorem prover, whose work
               is based on a set of logical axioms. The corresponding algorithm
               is combined with a shallow approach enriched with semantic information.
               Through the employment of logical methods, the recall and precision
               of the semantic patterns pertinent to the extracted relations
               can be increased considerably.},
  pdf       = {http://www.jlcl.org/2010_Heft1/tim_vorderbrueck.pdf},
  year      = {2010}
}

@misc{Luecking:Bergmann:2010,
  author    = {Andy L\"{u}cking and Kirsten Bergmann},
  title     = {Introducing the {B}ielefeld {SaGA} Corpus},
  howpublished = {Talk given at \textit{Gesture: Evolution, Brain, and
                   Linguistic Structures.} 4th Conference of the
                   International Society for Gesture Studies (ISGS).
                   Europa Universit\"{a}t Viadrina Frankfurt/Oder},
  abstract  = {People communicate multimodally. Most prominently, they co-produce
               speech and gesture. How do they do that? Studying the interplay
               of both modalities has to be informed by empirically observed
               communication behavior. We present a corpus built of speech and
               gesture data gained in a controlled study. We describe 1) the
               setting underlying the data; 2) annotation of the data; 3) reliability
               evalution methods and results; and 4) applications of the corpus
               in the research domain of speech and gesture alignment.},
  address   = {Europa Universit{\"a}t Viadrina Frankfurt/Oder},
  day       = {28},
  month     = {07},
  year      = {2010}
}

@inproceedings{Luecking:2010,
  author    = {Lücking, Andy},
  title     = {A Semantic Account for Iconic Gestures},
  booktitle = {Gesture: Evolution, Brain, and Linguistic Structures},
  pages     = {210},
  address   = {Europa Universit{\"a}t Viadrina Frankfurt/Oder},
  organization = {4th Conference of the International Society for
                   Gesture Studies (ISGS)},
  keywords  = {own},
  month     = {7},
  pdf       = {https://pub.uni-bielefeld.de/download/2318565/2319962},
  website   = {http://pub.uni-bielefeld.de/publication/2318565},
  year      = {2010}
}

@inproceedings{Luecking:et:al:2010,
  author    = {Lücking, Andy and Bergmann, Kirsten and Hahn, Florian and Kopp, Stefan
               and Rieser, Hannes},
  title     = {The Bielefeld Speech and Gesture Alignment Corpus (SaGA)},
  booktitle = {Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality},
  pages     = {92--98},
  address   = {Malta},
  organization = {7th International Conference for Language Resources
                   and Evaluation (LREC 2010)},
  abstract  = {People communicate multimodally. Most prominently, they co-produce
               speech and gesture. How do they do that? Studying the interplay
               of both modalities has to be informed by empirically observed
               communication behavior. We present a corpus built of speech and
               gesture data gained in a controlled study. We describe 1) the
               setting underlying the data; 2) annotation of the data; 3) reliability
               evalution methods and results; and 4) applications of the corpus
               in the research domain of speech and gesture alignment.},
  keywords  = {own},
  month     = {5},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/saga-corpus.pdf},
  website   = {http://pub.uni-bielefeld.de/publication/2001935},
  year      = {2010}
}

@inproceedings{Zahurul:Tiedemann:Eisele:2010,
  author    = {Islam, Md. Zahurul and Tiedemann, Jörg and Eisele, Andreas},
  title     = {English to Bangla Phrase – Based Machine Translation},
  booktitle = {The 14th Annual Conference of The European Association for Machine
               Translation. Saint-Raphaël, France, 27-28 May},
  owner     = {zahurul},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2015/08/English_to_Bangla_Phrase–Based_Machine_Translation.pdf},
  timestamp = {2011.08.02},
  year      = {2010}
}