@article{KunzeLemnitzerLuengenetal.2007, author = {Kunze, Claudia and Lemnitzer, Lothar and L{\"u}ngen, Harald and Storrer, Angelika}, title = {Repr{\"a}sentation und Verkn{\"u}pfung allgemeinsprachlicher und terminologischer Wortnetze in OWL}, series = {Zeitschrift f{\"u}r Sprachwissenschaft : Organ der Deutschen Gesellschaft f{\"u}r Sprachwissenschaft}, volume = {26}, number = {2}, publisher = {de Gruyter}, address = {Berlin}, issn = {1613-3706}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-8621}, pages = {267 -- 290}, year = {2007}, abstract = {This paper describes an approach to modelling a general-language wordnet, GermaNet, and a domain-specific wordnet, TermNet, in the web ontology language OWL. While the modelling process for GermaNet adopts relevant recommendations with respect to the English Princeton WordNet, for Term-Net an alternative modelling concept is developed that considers the special characteristics of domain-specific terminologies. We present a proposal for linking a general-language wordnet and a terminological wordnet within the framework of OWL and on this basis discuss problems and alternative modelling approaches.}, language = {de} } @misc{BeisswengerBartzStorreretal.2015, author = {Beißwenger, Michael and Bartz, Thomas and Storrer, Angelika and Westpfahl, Swantje}, title = {Tagset und Richtlinie f{\"u}r das PoSTagging von Sprachdaten aus Genres internetbasierter Kommunikation}, journal = {Tagset and guidelines for the PoS tagging of language data from genres of computermediated communication / social media}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-50650}, pages = {21}, year = {2015}, language = {de} } @incollection{LuengenBeisswengerSelzametal.2011, author = {L{\"u}ngen, Harald and Beißwenger, Michael and Selzam, Bianca and Storrer, Angelika}, title = {Modelling and Processing Wordnets in OWL}, series = {Modelling, Learning, and Processing of Text-Technological Data Structures}, editor = {Mehler, Alexander and K{\"u}hnberger, Kai-Uwe and Lobin, Henning and L{\"u}ngen, Harald and Storrer, Angelika and Witt, Andreas}, publisher = {Springer}, address = {Berlin/Heidelberg}, isbn = {978-3-642-22612-0}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-48322}, series = {Studies in Computational Intelligence}, number = {370}, pages = {347 -- 376}, year = {2011}, abstract = {In this contribution, we discuss and compare alternative options of modelling the entities and relations of wordnet-like resources in the Web Ontology Language OWL. Based on different modelling options, we developed three models of representing wordnets in OWL, i.e. the instance model, the dass model, and the metaclass model. These OWL models mainly differ with respect to the ontological Status of lexical units (word senses) and the synsets. While in the instance model lexical units and synsets are represented as individuals, in the dass model they are represented as classes; both model types can be encoded in the dialect OWL DL. As a third alternative, we developed a metaclass model in OWL FULL, in which lexical units and synsets are defined as metaclasses, the individuals of which are classes themselves. We apply the three OWL models to each of three wordnet-style resources: (1) a subset of the German wordnet GermaNet, (2) the wordnet-style domain ontology TermNet, and (3) GermaTermNet, in which TermNet technical terms and GermaNet synsets are connected by means of a set of "plug-in" relations. We report on the results of several experiments in which we evaluated the performance of querying and processing these different models: (1) A comparison of all three OWL models (dass, instance, and metaclass model) of TermNet in the context of automatic text-to-hypertext conversion, (2) an investigation of the potential of the GermaTermNet resource by the example of a wordnet-based semantic relatedness calculation.}, language = {en} } @article{SchneiderStorrerMehler2013, author = {Schneider, Roman and Storrer, Angelika and Mehler, Alexander}, title = {Editorial}, series = {Journal for Language Technology and Computational Linguistics}, volume = {28}, number = {2}, publisher = {GSCL}, address = {Regensburg}, issn = {2190-6858}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-48107}, pages = {III -- IV}, year = {2013}, language = {de} } @incollection{EichingerEisenbergKleinetal.2013, author = {Eichinger, Ludwig M. and Eisenberg, Peter and Klein, Wolfgang and Storrer, Angelika}, title = {Vorwort - Die deutsche Sprache ist wie sie ist}, series = {Reichtum und Armut der deutschen Sprache. Erster Bericht zur Lage der deutschen Sprache}, publisher = {De Gruyter}, address = {Berlin [u.a.]}, organization = {Deutsche Akademie f{\"u}r Sprache und Dichtung}, isbn = {978-3-11-033473-9}, doi = {https://doi.org/10.1515/9783110334739.5}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-59964}, pages = {5 -- 13}, year = {2013}, language = {de} } @inproceedings{BeisswengerChanierChiarietal.2016, author = {Beißwenger, Michael and Chanier, Thierry and Chiari, Isabella and Erjavec, Tomaž and Fišer, Darja and Herold, Axel and Ljubešić, Nikola and L{\"u}ngen, Harald and Poudat, C{\´e}line and Stemle, Egon W. and Storrer, Angelika and Wigham, Ciara}, title = {Integrating corpora of computer-mediated communication into the language resources landscape: Initiatives and best practices from French, German, Italian and Slovenian projects}, series = {Proceedings of the 5th CLARIN Annual Conference. Aix-en-Provence, France. 26-28 October, 2016}, editor = {Borin, Lars}, publisher = {CLARIN}, address = {Utrecht}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-58053}, pages = {5}, year = {2016}, abstract = {The paper presents best practices and results from projects in four countries dedicated to the creation of corpora of computer-mediated communication and social media interactions (CMC). Even though there are still many open issues related to building and annotating corpora of that type, there already exists a range of accessible solutions which have been tested in projects and which may serve as a starting point for a more precise discussion of how future standards for CMC corpora may (and should) be shaped like.}, language = {en} } @article{WolferBartzWeberetal.2016, author = {Wolfer, Sascha and Bartz, Thomas and Weber, Tassja and Abel, Andrea and Meyer, Christian M. and M{\"u}ller-Spitzer, Carolin and Storrer, Angelika}, title = {The effectiveness of lexicographic tools for optimising written L1-texts}, series = {International Journal of Lexicography}, edition = {First published online: October 14, 2016}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1477-4577}, doi = {10.1093/ijl/ecw038}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-55095}, pages = {28}, year = {2016}, abstract = {We present an empirical study addressing the question whether, and to which extent, lexicographic writing aids improve text revision results. German university students were asked to optimise two German texts using (1) no aids at all, (2) highlighted problems, or (3) highlighted problems accompanied by lexicographic resources that could be used to solve the specific problems. We found that participants from the third group corrected the largest number of problems and introduced the fewest semantic distortions during revision. Also, they reached the highest overall score and were most efficient (as measured in points per time). The second group with highlighted problems lies between the two other groups in almost every measure we analysed. We discuss these findings in the scope of intelligent writing environments, the effectiveness of writing aids in practical usage situations and teaching dictionary skills.}, language = {en} } @incollection{EngelbergStorrer2016, author = {Engelberg, Stefan and Storrer, Angelika}, title = {Typologie von Internetw{\"o}rterb{\"u}chern und -portalen}, series = {Internetlexikografie. Ein Kompendium}, publisher = {De Gruyter}, address = {Berlin u.a.}, isbn = {978-3-05-006423-9}, doi = {10.1515/9783050095615-004}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-53434}, pages = {31 -- 63}, year = {2016}, abstract = {Internetw{\"o}rterb{\"u}cher k{\"o}nnen viele Informationstypen auf neuartige Weise vereinigen und nutzeradaptiv pr{\"a}sentieren. Sie bilden in vernetzter Form als „Megaw{\"o}rterb{\"u}cher" große W{\"o}rterbuchportale und verschmelzen mit Korpora, multimedialen Erweiterungen und automatischen Sprachanalysetools zu Wortschatzinformationssystemen neuer Art. Es ist daher schwierig geworden, zwischen einen W{\"o}rterbuch einem Korpus, einem Atlas und einer Frequenzliste zu unterscheiden. Die Autoren versuchen, ein wenig Licht in das Dunkel der verschiedenen Typen von W{\"o}rterb{\"u}chern, W{\"o}rterbuchportalen und Wortschatzinformationssystemen zu bringen, und dabei auch zeigen, dass sich die Unordnung, die eine „Schl{\"o}raffe" in die Klassifikation des Tierreichs bringt, am Ende durchaus auszahlen kann.}, language = {de} } @inproceedings{BeisswengerEhrhardtHeroldetal.2016, author = {Beißwenger, Michael and Ehrhardt, Eric and Herold, Axel and L{\"u}ngen, Harald and Storrer, Angelika}, title = {Converting and Representing Social Media Corpora into TEI: Schema and best practices from CLARIN-D}, series = {TEI Conference and Members' Meeting 2016. Book of Abstracts}, editor = {Resch, Claudia and Hannesschl{\"a}ger, Vanessa and Wissik, Tanja}, publisher = {Austrian Centre for Digital Humanities, Austrian Academy of Sciences}, address = {Wien}, isbn = {978-3-200-04689-4}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-55736}, pages = {39 -- 41}, year = {2016}, abstract = {The paper presents results from a curation project within CLARIN-D, in which an existing lMWord corpus of German chat communication has been integrated into the DEREKO and DWDS corpus infrastructures of the CLARIN-D centres at the Institute for the German Language (IDS, Mannheim) and at the Berlin-Brandenburg Academy of Sciences (BBAW, Berlin). The focus is on the solutions developed for converting and representing the corpus in a TEI format.}, language = {en} } @incollection{LuengenBeisswengerEhrhardtetal.2016, author = {L{\"u}ngen, Harald and Beißwenger, Michael and Ehrhardt, Eric and Herold, Axel and Storrer, Angelika}, title = {Integrating corpora of computer-mediated communication in CLARIN-D: Results from the curation project ChatCorpus2CLARIN}, series = {Proceedings of the 13th Conference on Natural Language Processing (KONVENS)}, editor = {Dipper, Stefanie and Neubarth, Friedrich and Zinsmeister, Heike}, publisher = {Sprachwissenschaftliches Institut, Ruhr-Universit{\"a}t Bochum}, address = {Bochum}, issn = {2190-0949}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-55743}, series = {Bochumer Linguistische Arbeitsberichte}, number = {16}, pages = {156 -- 164}, year = {2016}, abstract = {We introduce our pipeline to integrate CMC and SM corpora into the CLARIN-D corpus infrastructure. The pipeline was developed by transforming an existing CMC corpus, the Dortmund Chat Corpus, into a resource conforming to current technical and legal standards. We describe how the resource has been prepared and restructured in terms of TEI encoding, linguistic annotations, and anonymisation. The output is a CLARIN-conformant resource integrated in the CLARIN-D research infrastructure.}, language = {en} }