Publikationen

[RSS Abonnement der Publikationsliste]

2018, forthcoming

  • C. Kantner and M. Overbeck, „The practical challenges of exploring ’soft‘ concepts through ‚hard‘ methods,“ European Journal of Political Research, 2018, forthcoming.
    [BibTeX]
    @article{methods,
    author = {Kantner, Cathleen and Overbeck, Maximilian},
    editor = {Puren, Marie and Lemke, Matthias},
    interhash = {69554f82aafc9724815cb78711eb503f},
    intrahash = {4bc1521df114e85f6ef6b4be98c79c3e},
    journal = {European Journal of Political Research},
    title = {The practical challenges of exploring 'soft' concepts through 'hard' methods},
    year = {2018, forthcoming}
    }

  • C. Kantner and M. Overbeck, „Die Analyse „weicher” Konzepte mit „harten” korpuslinguistischen Methoden.,“ in Big Data: Große Möglichkeiten oder große Probleme?, J. Behnke, A. Blaette, K. Schnapp, and C. Wagemann, Eds., Baden-Baden: Nomos Verlag, 2018, forthcoming.
    [BibTeX]
    @incollection{kantner2017,
    address = {Baden-Baden},
    author = {Kantner, Cathleen and Overbeck, Maximilian},
    booktitle = {Big Data: Große Möglichkeiten oder große Probleme?},
    editor = {Behnke, Joachim and Blaette, Andreas and Schnapp, Kai-Uwe and Wagemann, Claudius},
    interhash = {cb51d243b7fe28e74a2c28561d47698a},
    intrahash = {3372ba45c4c0e7af5ac7cbc6b2de70af},
    publisher = {Nomos Verlag},
    title = {Die Analyse „weicher” Konzepte mit „harten” korpuslinguistischen Methoden.},
    year = {2018, forthcoming}
    }

2018

  • M. Overbeck, „Vom Beobachter zum Teilnehmer: Europäische Mediendiskurse über Religion in bewaffneten Konflikten,“ in Das Narrativ von der Rückkehr der Religionen, H. Zapf, O. Hidalgo, and P. W. Hildmann, Eds., Wiesbaden: Springer Fachmedien Wiesbaden, 2018.
    [BibTeX] [Download PDF]
    @incollection{overbeck_beobachter,
    address = {Wiesbaden},
    author = {Overbeck, Maximilian},
    booktitle = {Das Narrativ von der Rückkehr der Religionen},
    editor = {Zapf, Holger and Hidalgo, Oliver and Hildmann, Philipp W.},
    interhash = {34f9d96413db884b58af0b8bea0aed7c},
    intrahash = {e3683ff7684a3004e2085581c7d56d73},
    publisher = {Springer Fachmedien Wiesbaden},
    title = {Vom Beobachter zum Teilnehmer: Europäische Mediendiskurse über Religion in bewaffneten Konflikten},
    url = {https://link.springer.com/chapter/10.1007/978-3-658-18451-3_10},
    year = 2018
    }

2017

  • J. Barnes, R. Klinger, and S. Schule im Walde, „Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets,“ in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Copenhagen, Denmark, 2017.
    [BibTeX]
    @inproceedings{Barnes2017,
    address = {Copenhagen, Denmark},
    author = {Barnes, Jeremy and Klinger, Roman and Schule im Walde, Sabine},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {ac69fc3da1cd095f0e25a83c9dd1237a},
    intrahash = {9785781c4f6f73d26526df8a24d638bd},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    title = {Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets},
    year = 2017
    }

  • F. Barth and S. Murr, „Digital Analysis of the Literary Reception of J.W. von Goethe’s Die Leiden des jungen Werthers.,“ in Digital Humanities 2017: Conference Abstracts, Montréal, Canada, 2017.
    [BibTeX]
    @inproceedings{murr2017,
    address = { Montréal, Canada},
    author = {Barth, Florian and Murr, Sandra},
    booktitle = {Digital Humanities 2017: Conference Abstracts},
    interhash = {caf3c24165a78328628df5654513f08f},
    intrahash = {fd9bff335fdcf70f506aa23fe9abb09c},
    month = {August},
    title = {Digital Analysis of the Literary Reception of J.W. von Goethe’s Die Leiden des jungen Werthers. },
    year = 2017
    }

  • A. Blessing, N. Echelmeyer, M. John, and N. Reiter, „An End-to-end Environment for Research Question-Driven Entity Extraction and Network Analysis,“ in Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, Vancouver, Canada, 2017, pp. 57-67. doi:10.18653/v1/W17-2208
    [BibTeX] [Download PDF]
    @inproceedings{Blessing2017aa,
    address = { Vancouver, Canada },
    author = {Blessing, Andre and Echelmeyer, Nora and John, Markus and Reiter, Nils},
    booktitle = { Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature },
    doi = {10.18653/v1/W17-2208},
    interhash = {f42a1b0c27d83ee36442330af2f3ffb7},
    intrahash = {832d1247fb039ce19e33a6bdc66c1023},
    month = { August },
    pages = { 57-67 },
    publisher = { Association for Computational Linguistics },
    title = {An End-to-end Environment for Research Question-Driven Entity Extraction and Network Analysis},
    url = {/brokenurl# http://www.aclweb.org/anthology/W/W17/W17-2208 },
    year = { 2017 }
    }

  • M. Braun and N. Reiter, „Sangsprüche auf Wörterwolken oder: Vorläufige Versuche zur Verbindung quantitativer und qualitativer Methoden bei der Erforschung mittelhochdeutscher Lyrik,“ in Sangspruchdichtung zwischen Reinmar von Zweter, Oswald von Wolkenstein und Michel Beheim, H. Brunner, F. Löser, and J. Franzke, Eds., Wiesbaden, Germany: Reichert Verlag, 2017, vol. 21, pp. 5-20.
    [BibTeX]
    @incollection{Braun2017aa,
    address = { Wiesbaden, Germany },
    author = {Braun, Manuel and Reiter, Nils},
    booktitle = { Sangspruchdichtung zwischen Reinmar von Zweter, Oswald von Wolkenstein und Michel Beheim },
    editor = {Brunner, Horst and Löser, Freimut and Franzke, Janina},
    interhash = {0b31588a8f0630a0ca1f80e55afb9c69},
    intrahash = {8bf86d58e56586037077bce0aec9138f},
    isbn = {978-3-95490-204-0},
    month = { April },
    pages = { 5-20 },
    publisher = { Reichert Verlag },
    series = { Jahrbuch der Oswald von Wolkenstein-Gesellschaft },
    title = {Sangsprüche auf Wörterwolken oder: Vorläufige Versuche zur Verbindung quantitativer und qualitativer Methoden bei der Erforschung mittelhochdeutscher Lyrik},
    volume = { 21 },
    year = { 2017 }
    }

  • N. Echelmeyer, N. Reiter, and S. Schulz, „Ein PoS-Tagger für "das" Mittelhochdeutsche,“ in DHd 2017 Konferenzabstracts, Bern, Schwitzerland, 2017, pp. 141-147.
    [BibTeX] [Abstract] [Download PDF]

    Mit diesem Beitrag möchten wir einen PoS-Tagger für das Mittelhochdeutsche vorstellen, der auf einem thematisch breiten und diachronen Korpus trainiert wurde. Als Tagset verwenden wir ein Inventar aus 17 universellen Wortart-Kategorien (Universal Dependency-Tagset, Nivre et al. 2016). Mit den annotierten Daten entwickeln wir ein Modell für den TreeTagger (Schmid 1995), das frei zugänglich gemacht wird. Dabei vergleichen wir drei verschiedene Möglichkeiten, den PoS-Tagger zu trainieren. Zunächst verwenden wir ein kleines, manuell annotiertes Trainingsset, vergleichen dessen Ergebnisse dann mit einem kleinen, automatisch disambiguierten Trainingsset und schließlich mit den maximal verfügbaren Daten. Mit dem Tagger möchten wir nicht nur eine „Marktlücke“ schließen (denn bisher gibt es keinen frei verwendbaren PoS-Tagger für das Mittelhochdeutsche), sondern auch eine größtmögliche Anwendbarkeit auf mittelhochdeutsche Texte verschiedener Gattungen, Jahrhunderte und regionaler Varietäten erreichen und weiteren Arbeiten mit mittelhochdeutschen Texten den Weg ebnen.

    @inproceedings{echelmeyer2017postagger,
    abstract = {Mit diesem Beitrag möchten wir einen PoS-Tagger für das Mittelhochdeutsche vorstellen, der auf einem thematisch breiten und diachronen Korpus trainiert wurde. Als Tagset verwenden wir ein Inventar aus 17 universellen Wortart-Kategorien (Universal Dependency-Tagset, Nivre et al. 2016). Mit den annotierten Daten entwickeln wir ein Modell für den TreeTagger (Schmid 1995), das frei zugänglich gemacht wird. Dabei vergleichen wir drei verschiedene Möglichkeiten, den PoS-Tagger zu trainieren. Zunächst verwenden wir ein kleines, manuell annotiertes Trainingsset, vergleichen dessen Ergebnisse dann mit einem kleinen, automatisch disambiguierten Trainingsset und schließlich mit den maximal verfügbaren Daten. Mit dem Tagger möchten wir nicht nur eine „Marktlücke“ schließen (denn bisher gibt es keinen frei verwendbaren PoS-Tagger für das Mittelhochdeutsche), sondern auch eine größtmögliche Anwendbarkeit auf mittelhochdeutsche Texte verschiedener Gattungen, Jahrhunderte und regionaler Varietäten erreichen und weiteren Arbeiten mit mittelhochdeutschen Texten den Weg ebnen.},
    address = {Bern, Schwitzerland},
    author = {Echelmeyer, Nora and Reiter, Nils and Schulz, Sarah},
    booktitle = {DHd 2017 Konferenzabstracts},
    interhash = {7d66653bf3ac0187f585987f534a25ac},
    intrahash = {3d21302e42bdfbe74e0edc3fe007573c},
    pages = {141 - 147},
    title = {Ein PoS-Tagger für "das" Mittelhochdeutsche},
    url = {http://www.ims.uni-stuttgart.de/forschung/ressourcen/werkzeuge/PoS_Tag_MHG.html},
    year = 2017
    }

  • M. Hartung, R. Klinger, J. Mohme, L. Vogel, and F. Schmidtke, „Ranking Right-Wing Extremist Social Media Profiles by Similarity to Democratic and Extremist Groups,“ in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Copenhagen, Denmark, 2017.
    [BibTeX] [Download PDF]
    @inproceedings{Hartung2017a,
    address = {Copenhagen, Denmark},
    author = {Hartung, Matthias and Klinger, Roman and Mohme, Julian and Vogel, Lars and Schmidtke, Franziska},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {2471bf1148fb27848a4ae9f34d93534b},
    intrahash = {caa23eb23d1a01b39e62a9fd4bd0225c},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    title = {Ranking Right-Wing Extremist Social Media Profiles by Similarity to Democratic and Extremist Groups},
    url = {http://aclweb.org/anthology/W/W17/W17-5204.pdf},
    year = 2017
    }

  • M. Hartung, R. Klinger, F. Schmidtke, and L. Vogel, „Identifying Right-Wing Extremism in German Twitter Profiles: a Classification Approach,“ in Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017, Proceedings, Cham, 2017, pp. 320-325.
    [BibTeX] [Download PDF]
    @inproceedings{Hartung2017,
    address = {Cham},
    author = {Hartung, Matthias and Klinger, Roman and Schmidtke, Franziska and Vogel, Lars},
    booktitle = {Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017, Proceedings},
    editor = {Frasincar, Flavius and Ittoo, Ashwin and Nguyen, Le Minh and Métais, Elisabeth},
    interhash = {5f3f12be6eb4013165833920005398ee},
    intrahash = {46d57ac77c3dfce4b682c0d0e9b1ed77},
    pages = {320--325},
    pdf = {http://www.romanklinger.de/publications/hartung2017-NLDB-short.pdf},
    publisher = {Springer International Publishing},
    title = {Identifying Right-Wing Extremism in German Twitter Profiles: a Classification Approach},
    url = {http://dx.doi.org/10.1007/978-3-319-59569-6_40},
    year = 2017
    }

  • F. Heimerl, M. John, Q. Han, S. Koch, and T. Ertl, „DocuCompass: Effective Exploration of Document Landscapes,“ IEEE Transactions on Visualization and Computer Graphics, 2017.
    [BibTeX] [Abstract]

    The creation of interactive visualization to analyze text documents has gained an impressive momentum in recent years. This is not surprising in the light of massive and still increasing amounts of available digitized texts. Websites, social media, news wire, and digital libraries are just few examples of the diverse text sources whose visual analysis and exploration offers new opportunities to effectively mine and manage the information and knowledge hidden within them. A popular visualization method for large text collections is to represent each document by a glyph in 2D space. These landscapes can be the result of optimizing pairwise distances in 2D to represent document similarities, or they are provided directly as meta data, such as geo-locations. For well-defined information needs, suitable interaction methods are available for these spatializations. However, free exploration and navigation on a level of abstraction between a labeled document spatialization and reading single documents is largely unsupported. As a result, vital foraging steps for task-tailored actions, such as selecting subgroups of documents for detailed inspection, or subsequent sense-making steps are hampered. To fill in this gap, we propose DocuCompass, a focus+context approach based on the lens metaphor. It comprises multiple methods to characterize local groups of documents, and to efficiently guide exploration based on users‘ requirements. DocuCompass thus allows for effective interactive exploration of document landscapes without disrupting the mental map of users by changing the layout itself. We discuss the suitability of multiple navigation and characterization methods for different spatializations and texts. Finally, we provide insights generated through user feedback and discuss the effectiveness of our approach.

    @article{noauthororeditor,
    abstract = {The creation of interactive visualization to analyze text documents has gained an impressive momentum in recent years.
    This is not surprising in the light of massive and still increasing amounts of available digitized texts.
    Websites, social media, news wire, and digital libraries are just few examples of the diverse text sources whose visual analysis and exploration offers new opportunities to effectively mine and manage the information and knowledge hidden within them.
    A popular visualization method for large text collections is to represent each document by a glyph in 2D space.
    These landscapes can be the result of optimizing pairwise distances in 2D to represent document similarities, or they are provided directly as meta data, such as geo-locations.
    For well-defined information needs, suitable interaction methods are available for these spatializations.
    However, free exploration and navigation on a level of abstraction between a labeled document spatialization and reading single documents is largely unsupported.
    As a result, vital foraging steps for task-tailored actions, such as selecting subgroups of documents for detailed inspection, or subsequent sense-making steps are hampered.
    To fill in this gap, we propose DocuCompass, a focus+context approach based on the lens metaphor.
    It comprises multiple methods to characterize local groups of documents, and to efficiently guide exploration based on users' requirements.
    DocuCompass thus allows for effective interactive exploration of document landscapes without disrupting the mental map of users by changing the layout itself.
    We discuss the suitability of multiple navigation and characterization methods for different spatializations and texts.
    Finally, we provide insights generated through user feedback and discuss the effectiveness of our approach.},
    author = {Heimerl, Florian and John, Markus and Han, Qi and Koch, Steffen and Ertl, Thomas},
    interhash = {d6457d13954d6aefb50c5b7ef91cfb35},
    intrahash = {79820e1562a3b7af96d90ebb328ba161},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    title = {DocuCompass: Effective Exploration of Document Landscapes},
    year = 2017
    }

  • E. Kim, S. Padó, and R. Klinger, „Prototypical Emotion Developments in Literary Genres,“ in Digital Humanities 2017: Conference Abstracts, Montréal, Canada, 2017.
    [BibTeX]
    @inproceedings{Kim2017,
    address = {Montréal, Canada},
    author = {Kim, Evgeny and Padó, Sebastian and Klinger, Roman},
    booktitle = {Digital Humanities 2017: Conference Abstracts},
    interhash = {1b6975f7865deb345eb953fea2f88a61},
    intrahash = {a067a8ffd2c65b5f5718dd9e6fc90178},
    month = {August},
    note = {accepted},
    organization = {McGill University and Universit\'e de Montr\'eal},
    pdf = {http://www.romanklinger.de/publications/kim2017.pdf},
    title = {Prototypical Emotion Developments in Literary Genres},
    year = 2017
    }

  • E. Kim, S. Padó, and R. Klinger, „Investigating the Relationship between Literary Genres and Emotional Plot Development,“ in Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL), 2017.
    [BibTeX]
    @inproceedings{Kim2017a,
    author = {Kim, Evgeny and Pad\'o, Sebastian and Klinger, Roman},
    booktitle = {Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL)},
    interhash = {b1155337d03bd6696be183baf88015f7},
    intrahash = {df4c574b509be6aa5ddffce416ebe758},
    organization = {Association for Computational Linguistics},
    pdf = {http://www.romanklinger.de/publications/kim2017a.pdf},
    title = {Investigating the Relationship between Literary Genres and Emotional Plot Development},
    year = 2017
    }

  • R. Klinger, „Does Optical Character Recognition and Caption Generation Improve Emotion Detection in Microblog Posts?,“ in Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017, Cham, 2017, pp. 313-319.
    [BibTeX] [Download PDF]
    @inproceedings{Klinger2017,
    address = {Cham},
    author = {Klinger, Roman},
    booktitle = {Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017},
    editor = {Frasincar, Flavius and Ittoo, Ashwin and Nguyen, Le Minh and Métais, Elisabeth},
    interhash = {1a5ce7064cbb2074132171cdb23164b3},
    intrahash = {11363b658eef4d5ee66cf8b13df05277},
    pages = {313--319},
    pdf = {http://www.romanklinger.de/publications/klinger2017-nldb.pdf},
    publisher = {Springer International Publishing},
    title = {Does Optical Character Recognition and Caption Generation Improve Emotion Detection in Microblog Posts?},
    url = {http://dx.doi.org/10.1007/978-3-319-59569-6_39},
    year = 2017
    }

  • K. Kurzhals, M. John, F. Heimerl, P. Kuznecov, and D. Weiskop, „Visual Movie Analytics,“ in IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 18, 2017, p. 51.
    [BibTeX] [Abstract]

    The analysis of inherent structures of movies plays an important role in studying stylistic devices and specific, content-related questions. Examples are the analysis of personal constellations in movie scenes, dialogue-based content analysis, or the investigation of image-based features. We provide a visual analytics approach that supports the analytical reasoning process to derive higher level insights about the content on a semantic level. Combining automatic methods for semantic scene analysis based on script and subtitle text, we perform a low-level analysis of the data automatically. Our approach features an interactive visualization that allows a multilayer interpretation of descriptive features to characterize movie content. For semantic analysis, we extract scene information from movie scripts and match them with the corresponding subtitles. With text- and image-based query techniques, we facilitate an interactive comparison of different movie scenes on an image and on a semantic level. We demonstrate how our approach can be applied for content analysis on a popular Hollywood movie.

    @inproceedings{conf/siggraph/Huh96,
    abstract = {The analysis of inherent structures of movies plays
    an important role in studying stylistic devices and specific,
    content-related questions. Examples are the analysis of personal
    constellations in movie scenes, dialogue-based content analysis,
    or the investigation of image-based features. We provide a visual
    analytics approach that supports the analytical reasoning process
    to derive higher level insights about the content on a semantic
    level. Combining automatic methods for semantic scene analysis
    based on script and subtitle text, we perform a low-level analysis
    of the data automatically. Our approach features an interactive
    visualization that allows a multilayer interpretation of descriptive
    features to characterize movie content. For semantic analysis, we
    extract scene information from movie scripts and match them with
    the corresponding subtitles. With text- and image-based query
    techniques, we facilitate an interactive comparison of different
    movie scenes on an image and on a semantic level. We demonstrate
    how our approach can be applied for content analysis on a popular
    Hollywood movie.},
    author = {Kurzhals, Kuno and John, Markus and Heimerl, Florian and Kuznecov, Paul and Weiskop, Daniel},
    booktitle = {IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 18},
    interhash = {b5d426101d290c9be0f34bb94afa732c},
    intrahash = {31c5727eb88426afb28ed3dd780d71bc},
    pages = 51,
    title = {Visual Movie Analytics},
    year = 2017
    }

  • M. Köper, E. Kim, and R. Klinger, „IMS at EmoInt-2017: Emotion Intensity Prediction with Affective Norms, Automatically Extended Resources and Deep Learning,“ in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Copenhagen, Denmark, 2017.
    [BibTeX] [Download PDF]
    @inproceedings{Koeper2017,
    address = {Copenhagen, Denmark},
    author = {K\"oper, Maximilian and Kim, Evgeny and Klinger, Roman},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {21cc4e2239a9bfcb2d880d865e7400b9},
    intrahash = {633fcb7560b743251a73b99fcd8617c4},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    title = {{IMS} at {EmoInt-2017}: Emotion Intensity Prediction
    with Affective Norms, Automatically Extended
    Resources and Deep Learning},
    url = {http://aclweb.org/anthology/W/W17/W17-5206.pdf},
    year = 2017
    }

  • N. Reiter, S. Schulz, G. Kremer, R. Klinger, G. Viehhauser, and J. Kuhn, „Teaching Computational Aspects in the Digital Humanities Program at University of Stuttgart — Intentions and Experiences,“ in Proceedings of the GSCL Workshop on Teaching NLP for Digital Humanities (Teach4DH 2017), 2017.
    [BibTeX] [Download PDF]
    @inproceedings{Viehhauser2017,
    author = {Reiter, Nils and Schulz, Sarah and Kremer, Gerhard and Klinger, Roman and Viehhauser, Gabriel and Kuhn, Jonas},
    booktitle = {Proceedings of the GSCL Workshop on Teaching NLP for Digital Humanities (Teach4DH 2017)},
    interhash = {383ce9948347f0cba3dc027823047aab},
    intrahash = {0fa2d6c1246dfa5403998794243ca148},
    pdf = {http://www.romanklinger.de/publications/teach4dhpaper2017.pdf},
    title = {Teaching Computational Aspects in the Digital Humanities
    Program at University of Stuttgart -- Intentions and
    Experiences},
    url = {http://ceur-ws.org/Vol-1918/reiter.pdf},
    year = 2017
    }

  • N. Reiter, J. Kuhn, and M. Willand, „To GUI or not to GUI?,“ in INFORMATIK 2017, Chemnitz, Germany, 2017, pp. 1179-1184. doi:10.18420/in2017_119
    [BibTeX]
    @inproceedings{Reiter2017ac,
    address = { Chemnitz, Germany },
    author = {Reiter, Nils and Kuhn, Jonas and Willand, Marcus},
    booktitle = { INFORMATIK 2017 },
    doi = {10.18420/in2017_119},
    editor = {Eibl, Maximilian and Gaedke, Martin},
    interhash = {386b69fa2beeaf379a07f1f655aaf883},
    intrahash = {586d900175fc399e7f7e8a666770849d},
    isbn = {978-3-88579-669-5},
    month = { September },
    pages = { 1179-1184 },
    publisher = { Gesellschaft für Informatik e.V. },
    series = { Lecture Notes in Informatics (LNI) },
    title = {To GUI or not to GUI?},
    volume = { 275 },
    year = { 2017 }
    }

  • N. Reiter, E. Gius, J. Strötgen, and M. Willand, „A Shared Task for a Shared Goal – Systematic Annotation of Literary Texts,“ in Digital Humanities 2017: Conference Abstracts, Montreal, Canada, 2017.
    [BibTeX]
    @inproceedings{reiter2017shared,
    address = { Montreal, Canada },
    author = {Reiter, Nils and Gius, Evelyn and Strötgen, Jannik and Willand, Marcus},
    booktitle = { Digital Humanities 2017: Conference Abstracts },
    interhash = {1c650a67e135cbefcddbf25f6b5c3c29},
    intrahash = {92eb79bf73357b1b687008f0a0f4f35a},
    month = {August},
    note = {accepted},
    title = { A Shared Task for a Shared Goal - Systematic Annotation of Literary Texts },
    year = { 2017 }
    }

  • H. Schuff, J. Barnes, J. Mohme, S. Padó, and R. Klinger, „Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus,“ in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Copenhagen, Denmark, 2017.
    [BibTeX] [Download PDF]
    @inproceedings{Schuff2017,
    address = {Copenhagen, Denmark},
    author = {Schuff, Hendrik and Barnes, Jeremy and Mohme, Julian and Pad\'o, Sebastian and Klinger, Roman},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {9e6b46c1b864a8b7fa4a2489d67bd66c},
    intrahash = {94122d40f411f8a4ca723e82b3f55ea6},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    title = {Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus},
    url = {http://aclweb.org/anthology/W/W17/W17-5203.pdf},
    year = 2017
    }

  • M. Sänger, U. Leser, and R. Klinger, „Fine-grained Opinion Mining from Mobile App Reviews with Word Embedding Features,“ in Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017, Proceedings, Cham, 2017, pp. 3-14.
    [BibTeX] [Download PDF]
    @inproceedings{Saenger2017,
    address = {Cham},
    author = {Sänger, Mario and Leser, Ulf and Klinger, Roman},
    booktitle = {Natural Language Processing and Information Systems: 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017, Liège, Belgium, June 21-23, 2017, Proceedings},
    editor = {Frasincar, Flavius and Ittoo, Ashwin and Nguyen, Le Minh and Métais, Elisabeth},
    interhash = {c42a2564e1acfbcdc7f1f0e6c935d8e6},
    intrahash = {6c4ac476a2427f91a766742356068e69},
    pages = {3--14},
    pdf = {http://www.romanklinger.de/publications/saenger2017-nldb.pdf},
    publisher = {Springer International Publishing},
    title = {Fine-grained Opinion Mining from Mobile App Reviews with Word Embedding Features},
    url = {http://dx.doi.org/10.1007/978-3-319-59569-6_1},
    year = 2017
    }

  • M. Willand and N. Reiter, „Geschlecht und Gattung. Digitale Analysen von Kleists ›Familie Schroffenstein‹,“ in Kleist-Jahrbuch 2017, A. Allerkamp, G. Blamberger, I. Breuer, B. Gribnitz, H. L. Lund, and M. Roussel, Eds., Stuttgart, Germany: J.B. Metzler, 2017, pp. 142-160. doi:10.1007/978-3-476-04516-4_16
    [BibTeX]
    @incollection{Willand2017aa,
    address = { Stuttgart, Germany },
    author = {Willand, Marcus and Reiter, Nils},
    booktitle = { Kleist-Jahrbuch 2017 },
    doi = {10.1007/978-3-476-04516-4_16},
    editor = {Allerkamp, Andrea and Blamberger, Günter and Breuer, Ingo and Gribnitz, Barbara and Lund, Hannah Lotte and Roussel, Martin},
    interhash = {2ad69d37f248b0829aef40ce429f3862},
    intrahash = {e439e03ae5d7ab58d3e436fb223e3bbe},
    month = { September },
    pages = { 142-160 },
    publisher = { J.B. Metzler },
    series = { Kleist-Jahrbuch },
    title = {Geschlecht und Gattung. Digitale Analysen von Kleists ›Familie Schroffenstein‹},
    year = { 2017 }
    }

2016

  • A. Blessing and J. Kuhn, „Crosslingual Textual Emigration Analysis,“ in Digital Humanities 2016: Conference Abstracts, Jagiellonian University & Pedagogical University, Kraków, 2016, pp. 744-745.
    [BibTeX] [Abstract] [Download PDF]

    The presented work describes the adaptation of a Natural Language Processing (NLP) based biographical data exploration system to a new language. We argue that such a transfer step has many characteristic properties of a typical challenge in the Digital Humanities (DH): Resources and tools of different origin and with different accuracy are combined for their use in a multidisciplinary context. Hence, we view the project context as an interesting test-bed for a few methodological considerations.

    @inproceedings{Blessing:2016ab,
    abstract = {The presented work describes the adaptation of a Natural Language Processing (NLP) based biographical data exploration system to a new language. We argue that such a transfer step has many characteristic properties of a typical challenge in the Digital Humanities (DH): Resources and tools of different origin and with different accuracy are combined for their use in a multidisciplinary context. Hence, we view the project context as an interesting test-bed for a few methodological considerations.},
    address = {Jagiellonian University \& Pedagogical University, Krak{\'o}w},
    author = {Blessing, Andre and Kuhn, Jonas},
    booktitle = {Digital Humanities 2016: Conference Abstracts},
    interhash = {c27db04362a3f04c64a95731d7c95c1b},
    intrahash = {45b7812a28f0e562934041ac14947f9f},
    pages = {744-745},
    title = {Crosslingual Textual Emigration Analysis},
    url = {http://dh2016.adho.org/abstracts/50},
    year = 2016
    }

  • M. El-Assady, V. Gold, M. John, T. Ertl, and D. Keim, „Visual Text Analytics in Context of Digital Humanities,“ Published at the 1st IEEE VIS Workshop on Visualization for the Digital Humanities as part of the IEEE VIS 2016, 2016.
    [BibTeX] [Abstract]

    Digital Humanities (DH) research brings together scholars from different disciplines to work on tackling a common research challenge. Hence, DH-projects have to overcome common challenges of multi-disciplinary research, such as methodological differences or communication issues. However, in contrast to interdisciplinary collaborations from related fields of science, in the digital humanities, a gap between qualitative scholarship traditions and quantitative data-driven research has to be bridged to achieve a common goal. With this position paper, we aim at starting a discussion between the various involved disciplines in the digital humanities on how to approach the problem-solving process in DH-projects. Based on our experience in different visual text analytics projects and extensive two years of discussions, we propose an abstract conceptual workflow as a best practice for digital humanities projects.

    @article{noauthororeditor,
    abstract = {Digital Humanities (DH) research brings together scholars from different disciplines to work on tackling a common research
    challenge. Hence, DH-projects have to overcome common challenges of multi-disciplinary research, such as methodological differences
    or communication issues. However, in contrast to interdisciplinary collaborations from related fields of science, in the digital humanities,
    a gap between qualitative scholarship traditions and quantitative data-driven research has to be bridged to achieve a common goal.
    With this position paper, we aim at starting a discussion between the various involved disciplines in the digital humanities on how to
    approach the problem-solving process in DH-projects. Based on our experience in different visual text analytics projects and extensive
    two years of discussions, we propose an abstract conceptual workflow as a best practice for digital humanities projects.},
    author = {El-Assady, Mennatallah and Gold, Valentin and John, Markus and Ertl, Thomas and Keim, Daniel},
    interhash = {dc805711a2872f0dc48b876396a446f7},
    intrahash = {6784079c89f2d42527d30c9ddd81ff56},
    journal = {Published at the 1st IEEE VIS Workshop on Visualization for the Digital Humanities as part of the IEEE VIS 2016},
    title = {Visual Text Analytics in Context of Digital Humanities
    },
    year = 2016
    }

  • G. Heyer, C. Kantner, A. Niekler, and M. Overbeck, „Modeling the dynamics of domain specific terminology in diachronic corpora,“ in Proceedings of the 12th International conference on Terminology and Knowledge Engineering (TKE 2016), 2016.
    [BibTeX]
    @inproceedings{heyermodeling,
    author = {Heyer, Gerhard and Kantner, Cathleen and Niekler, Andreas and Overbeck, Maximilian},
    booktitle = {Proceedings of the 12th International conference on Terminology and Knowledge Engineering (TKE 2016)},
    interhash = {dd3836d7818f4d9dd331fd3da5f45f45},
    intrahash = {c1bc0d432b83dfdb869109b35c96f813},
    title = {Modeling the dynamics of domain specific terminology in diachronic corpora},
    year = 2016
    }

  • M. John, S. Lohmann, S. Koch, M. Wörner, and T. Ertl, „Visual Analytics for Narrative Text Visualizing Characters and their Relationships as Extracted from Novels,“ In Proceedings of the 6th International Conference on Information Visualization Theory and Applications, 2016.
    [BibTeX] [Abstract]

    The study of novels and the analysis of their plot, characters and other entities are time-consuming and complex tasks in literary science. The digitization of literature and the proliferation of electronic books provide new opportunities to support these tasks with visual abstractions. Methods from the fields of computational linguistics can be used to automatically extract entities and their relations from digitized novels, which can then be visualized to ease exploration and analysis tasks. This paper presents a web-based approach that combines automatic analysis methods with effective visualization techniques. Different views on the extracted entities are provided and relations between them across the plot are indicated. Two usage scenarios show successful applications of the approach and demonstrate its benefits and limitations.

    @article{noauthororeditor,
    abstract = {The study of novels and the analysis of their plot, characters and other entities are time-consuming and complex
    tasks in literary science. The digitization of literature and the proliferation of electronic books provide
    new opportunities to support these tasks with visual abstractions. Methods from the fields of computational linguistics
    can be used to automatically extract entities and their relations from digitized novels, which can then
    be visualized to ease exploration and analysis tasks. This paper presents a web-based approach that combines
    automatic analysis methods with effective visualization techniques. Different views on the extracted entities
    are provided and relations between them across the plot are indicated. Two usage scenarios show successful
    applications of the approach and demonstrate its benefits and limitations.},
    author = {John, Markus and Lohmann, Steffen and Koch, Steffen and Wörner, Michael and Ertl, Thomas},
    interhash = {2d94ee951b425ccdc4c9dad2787b8042},
    intrahash = {b1f872da093bff4f949ba42c67bfb1b0},
    journal = {In Proceedings of the 6th International Conference on Information Visualization Theory and Applications},
    title = {Visual Analytics for Narrative Text
    Visualizing Characters and their Relationships as Extracted from Novels},
    year = 2016
    }

  • C. Kantner, J. Kuhn, A. Blessing, and M. Overbeck, „Die Anwendung computer- und korpuslinguistischer Methoden für eine interaktive und flexible Tiefenanalyse der Mobilisierung kollektiver Identitäten in öffentlichen Debatten über Krieg und Frieden – e-Identity,“ in Jahrestagung der Digital Humanities im deutschsprachigen Raum (DHd), 2016.
    [BibTeX]
    @inproceedings{kantneranwendung,
    author = {Kantner, Cathleen and Kuhn, Jonas and Blessing, Andre and Overbeck, Maximilian},
    booktitle = {Jahrestagung der Digital Humanities im deutschsprachigen Raum (DHd)},
    interhash = {54c41b9ae544e537c6eda47c449d6be2},
    intrahash = {9bb37edbb6fd8b29aa03025186c54c87},
    title = {Die Anwendung computer- und korpuslinguistischer Methoden für eine interaktive und flexible Tiefenanalyse der Mobilisierung kollektiver Identitäten in öffentlichen Debatten über Krieg und Frieden - e-Identity},
    year = 2016
    }

  • R. Klinger, S. S. Suliya, and N. Reiter, „Automatic Emotion Detection for Quantitative Literary Studies — A case study based on Franz Kafka’s “Das Schloss” und “Amerika”,“ in Digital Humanities Book of Abstracts, 2016.
    [BibTeX] [Download PDF]
    @inproceedings{klinger2016automatic,
    author = {Klinger, Roman and Suliya, Surayya Samat and Reiter, Nils},
    booktitle = {Digital Humanities Book of Abstracts},
    interhash = {30b63ec5db28f03449729cffd98a2ea6},
    intrahash = {9cffd7d8588a092a581097615105e20e},
    title = {Automatic Emotion
    Detection for Quantitative Literary Studies -- A case study based on
    Franz Kafka's “Das Schloss” und “Amerika”},
    url = {http://www.romanklinger.de/publications/klinger-samat-reiter2016.pdf},
    year = 2016
    }

  • R. Klinger, S. S. Suliya, and N. Reiter, „Automatic Emotion Detection for Quantitative Literary Studies — A case study based on Franz Kafka’s „Das Schloss“ and „Amerika“,“ in Digital Humanities 2016: Conference Abstracts, Kraków, Poland, 2016, pp. 826-828.
    [BibTeX] [Download PDF]
    @inproceedings{Klinger2016,
    address = {Krak\'ow, Poland},
    author = {Klinger, Roman and Suliya, Surayya Samat and Reiter, Nils},
    booktitle = {Digital Humanities 2016: Conference Abstracts},
    interhash = {f31473c37c8ba97062910c7d4bb2590c},
    intrahash = {521aaec63f1fc7bd58d6568750070eba},
    month = {July},
    organization = {Jagiellonian University and Pedagogical University},
    pages = {826--828},
    title = {Automatic Emotion Detection for Quantitative Literary Studies --  A case study based on Franz Kafka's ``Das Schloss'' and ``Amerika''},
    url = {http://dh2016.adho.org/abstracts/318},
    year = 2016
    }

  • J. Kuhn, A. Alexiadou, M. Braun, T. Ertl, S. Holtz, C. Kantner, C. Misselhorn, S. Padó, S. Richter, A. Stein, and C. Zittel, „CRETA (Centrum für reflektierte Textanalyse) – Fachübergreifende Methodenentwicklung in den Digital Humanities,“ in Proceedings of DHd, Leipzig, Germany, 2016.
    [BibTeX]
    @inproceedings{kuhn2016creta,
    address = {Leipzig, Germany},
    author = {Kuhn, Jonas and Alexiadou, Artemis and Braun, Manuel and Ertl, Thomas and Holtz, Sabine and Kantner, Cathleen and Misselhorn, Catrin and Padó, Sebastian and Richter, Sandra and Stein, Achim and Zittel, Claus},
    booktitle = {Proceedings of DHd},
    interhash = {5ec0e3be951b3aa031535222f127f0a2},
    intrahash = {cad8e439eb38f7e41548e99fe223523e},
    month = {March},
    title = {CRETA (Centrum für reflektierte Textanalyse) – Fachübergreifende Methodenentwicklung in den Digital Humanities},
    year = 2016
    }

  • D. Le, N. T. Vu, and A. Blessing, „Towards a text analysis system for political debates,“ in Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, Berlin, Germany, 2016, pp. 134-139.
    [BibTeX] [Abstract] [Download PDF]

    Social scientists and journalists nowadays have to deal with an increasingly large amount of data. It usually requires expensive searching and annotation effort to find insight in a sea of information. Our goal is to build a discourse analysis system which can be applied to large text collections. This system can help social scientists and journalists to analyze data and validate their research theories by providing them with tailored machine learning methods to alleviate the annotation effort and exploratory facilities and visualization tools. We report initial experimental results in a case study related to discourse analysis in political debates.

    @inproceedings{le-vu-blessing:2016:LaTeCH,
    abstract = {Social scientists and journalists nowadays have to deal with an increasingly large amount of data. It usually requires expensive searching and annotation effort to find insight in a sea of information. Our goal is to build a discourse analysis system which can be applied to large text collections. This system can help social scientists and journalists to analyze data and validate their research theories by providing them with tailored machine learning methods to alleviate the annotation effort and exploratory facilities and visualization tools. We report initial experimental results in a case study related to discourse analysis in political debates.},
    address = {Berlin, Germany},
    author = {Le, Dieu-Thu and Vu, Ngoc Thang and Blessing, Andre},
    booktitle = {Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities},
    interhash = {a9fe53c22c939f4f35eeb96281c3aa09},
    intrahash = {5f8ec62ef3cc56dce5b2a5da6a2c5ba1},
    month = {August},
    pages = {134--139},
    publisher = {Association for Computational Linguistics},
    title = {Towards a text analysis system for political debates},
    url = {http://anthology.aclweb.org/W16-2117},
    year = 2016
    }

  • J. Ling and R. Klinger, „An Empirical, Quantitative Analysis of the Differences Between Sarcasm and Irony,“ in The Semantic Web: ESWC 2016 Satellite Events, Heraklion, Crete, Greece, May 29 — June 2, 2016, Revised Selected Papers, 2016, pp. 203-216.
    [BibTeX] [Download PDF]
    @inproceedings{Ling2016,
    author = {Ling, Jennifer and Klinger, Roman},
    booktitle = {The Semantic Web: ESWC 2016 Satellite Events, Heraklion, Crete, Greece, May 29 -- June 2, 2016, Revised Selected Papers},
    editor = {Sack, Harald and Rizzo, Giuseppe and Steinmetz, Nadine and Mladeni{\'{c}}, Dunja and Auer, S{\"o}ren and Lange, Christoph},
    interhash = {f576a431b1c9eb41c03125538e04d18b},
    intrahash = {a565f08265f08e955343158dd7a88b9b},
    pages = {203--216},
    pdf = {http://www.romanklinger.de/publications/ling2016.pdf},
    publisher = {Springer International Publishing},
    series = {Lecture Notes in Computer Science},
    title = {An Empirical, Quantitative Analysis of the Differences Between Sarcasm and Irony},
    url = {http://dx.doi.org/10.1007/978-3-319-47602-5_39},
    year = 2016
    }

  • I. Rösiger and J. Kuhn, „IMS HotCoref DE: A Data-driven Co-reference Resolver for German.,“ in LREC, 2016.
    [BibTeX] [Download PDF]
    @inproceedings{conf/lrec/RoesigerK16,
    author = {Rösiger, Ina and Kuhn, Jonas},
    booktitle = {LREC},
    crossref = {conf/lrec/2016},
    editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, Hélène and Moreno, Asunción and Odijk, Jan and Piperidis, Stelios},
    ee = {http://www.lrec-conf.org/proceedings/lrec2016/summaries/633.html},
    interhash = {916e8cc1ff84eb42c7139d139de88097},
    intrahash = {63fd8c895ab9d291ab270d739371e160},
    publisher = {European Language Resources Association (ELRA)},
    title = {IMS HotCoref DE: A Data-driven Co-reference Resolver for German.},
    url = {http://dblp.uni-trier.de/db/conf/lrec/lrec2016.html#RoesigerK16},
    year = 2016
    }

  • C. Scheible, R. Klinger, and S. Padó, „Model Architectures for Quotation Detection,“ in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, 2016, pp. 1736-1745.
    [BibTeX] [Download PDF]
    @inproceedings{Scheible2016,
    address = {Berlin, Germany},
    author = {Scheible, Christian and Klinger, Roman and Pad\'{o}, Sebastian},
    booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
    interhash = {63a2139132dde0b43f5709271ec735c0},
    intrahash = {b0b55f48c4f762fa4e0f0bcc79960395},
    month = {August},
    pages = {1736--1745},
    publisher = {Association for Computational Linguistics},
    title = {Model Architectures for Quotation Detection},
    url = {http://www.aclweb.org/anthology/P16-1164},
    year = 2016
    }

  • S. Schulz and N. Reiter, „Authorship Attribution of Mediaeval German Text: Style and Contents in Apollonius von Tyrland,“ in Proceeding of Digital Humanities 2016, Krakau, 2016, pp. 883-885.
    [BibTeX] [Abstract]

    n this paper, we describe computer-aided authorship testing on the Middle High German (MHG) text Apollonius von Tyrland written by Heinrich von Neustadt (HvN) in the late 13th century. Being based on a Latin original, HvN is suspected to incorporate other sources into the translation. We investigate assumptions regarding a segmentation of this text into parts supposedly tracking back to different sources. Our objective is it to provide a) clarification on the validity of this segmentation and b) on features that show the difference in origin of the segments. In particular, we distinguish between features related to content and to style.

    @inproceedings{schulz2016c,
    abstract = {n this paper, we describe computer-aided authorship testing on the Middle High German (MHG) text Apollonius von Tyrland written by Heinrich von Neustadt (HvN) in the late 13th century. Being based on a Latin original, HvN is suspected to incorporate other sources into the translation. We investigate assumptions regarding a segmentation of this text into parts supposedly tracking back to different sources. Our objective is it to provide a) clarification on the validity of this segmentation and b) on features that show the difference in origin of the segments. In particular, we distinguish between features related to content and to style.},
    address = {Krakau},
    author = {Schulz, Sarah and Reiter, Nils},
    booktitle = {Proceeding of Digital Humanities 2016},
    interhash = {8612c781ea6516fe4f1c7c96d7f019e6},
    intrahash = {16bf2bc8a8a1dd6f6f38f87601004bec},
    month = {July},
    pages = {883-885},
    title = {Authorship Attribution of Mediaeval German Text: Style and Contents in Apollonius von Tyrland },
    year = 2016
    }

  • S. Schulz and M. Keller, „Code-Switching Ubique Est – Language Identification and Part-of-Speech Tagging for Historical Mixed Text,“ in Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, Berlin, Germany, 2016, pp. 43-51.
    [BibTeX] [Abstract] [Download PDF]

    In this paper, we describe the development of a language identification system and a part-of-speech tagger for Latin-Middle English mixed text. To this end, we annotate data with language IDs and Universal POS tags (Petrov et al., 2012). As a classifier, we train a conditional random field classifier for both sub-tasks, including features generated by the TreeTagger models of both languages. The focus lies on both a general and a task-specific evaluation. Moreover, we describe our effort concerning beyond proof-of-concept implementation of tools and towards a more task-oriented approach, showing how to apply our techniques in the context of Humanities research.

    @inproceedings{schulz-keller:2016:LaTeCH,
    abstract = {In this paper, we describe the development of a language identification system and a part-of-speech tagger for Latin-Middle English mixed text. To this end, we annotate data with language IDs and Universal POS tags (Petrov et al., 2012). As a classifier, we train a conditional random field classifier for both sub-tasks, including features generated by the TreeTagger models of both languages. The focus lies on both a general and a task-specific evaluation. Moreover, we describe our effort concerning beyond proof-of-concept implementation of tools and towards a more task-oriented approach, showing how to apply our techniques in the context of Humanities research.
    },
    address = {Berlin, Germany},
    author = {Schulz, Sarah and Keller, Mareike},
    booktitle = {Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities},
    interhash = {254d03475681d83d705b2c849f9a33ef},
    intrahash = {1e67f2505fd63a46d1ea35989927f23c},
    month = {August},
    pages = {43--51},
    publisher = {Association for Computational Linguistics},
    title = {Code-Switching Ubique Est - Language Identification and Part-of-Speech Tagging for Historical Mixed Text},
    url = {http://anthology.aclweb.org/W16-2105},
    year = 2016
    }

  • S. Schulz and J. Kuhn, „Learning from Within? Comparing PoS Tagging Approaches for Historical Text,“ in Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Slovenia, 2016.
    [BibTeX] [Abstract]

    In this paper, we investigate unsupervised and semi-supervised methods for part-of-speech (PoS) tagging in the context of historical German text. We locate our research in the context of Digital Humanities where the non-canonical nature of text causes issues facing an Natural Language Processing world in which tools are mainly trained on standard data. Data deviating from the norm requires tools adjusted to this data. We explore to which extend the availability of such training material and resources related to it influences the accuracy of PoS tagging. We investigate a variety of algorithms including neural nets, conditional random fields and self-learning techniques in order to find the best-fitted approach to tackle data sparsity. Although methods using resources from related languages outperform weakly supervised methods using just a few training examples, we can still reach a promising accuracy with methods abstaining additional resources.

    @inproceedings{schulz2016learning,
    abstract = {In this paper, we investigate unsupervised and semi-supervised methods for part-of-speech (PoS) tagging in the context of historical German text. We locate our research in the context of Digital Humanities where the non-canonical nature of text causes issues facing an Natural Language Processing world in which tools are mainly trained on standard data. Data deviating from the norm requires tools adjusted to this data. We explore to which extend the availability of such training material and resources related to it influences the accuracy of PoS tagging. We investigate a variety of algorithms including neural nets, conditional random fields and self-learning techniques in order to find the best-fitted approach to tackle data sparsity. Although methods using resources from related languages outperform weakly supervised methods using just a few training examples, we can still reach a promising accuracy with methods abstaining additional resources.},
    address = {Slovenia},
    author = {Schulz, Sarah and Kuhn, Jonas},
    booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
    editor = {Chair), Nicoletta Calzolari (Conference and Choukri, Khalid and Declerck, Thierry and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
    interhash = {305cbe7b196649541c3a42af40a09625},
    intrahash = {d8e04f51ca5cc496f20cf534ef8ebe4d},
    month = may,
    publisher = {European Language Resources Association (ELRA)},
    title = {Learning from Within? Comparing PoS Tagging Approaches for Historical Text},
    year = 2016
    }

  • A. Stein, „Old French Dependency Parsing: Results of Two Parsers, Analysed from a Linguistic Point of View,“ in Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), 23.-28.5.2016, Portoroz, Slovenia, 2016.
    [BibTeX] [Download PDF]
    @inproceedings{Stein:2016,
    address = {Portoroz, Slovenia},
    author = {Stein, Achim},
    booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), 23.-28.5.2016},
    editor = {Calzolari, Nicoletta and others},
    interhash = {3791cd16a1513581ed3a6827e3dd9a2f},
    intrahash = {f1167834b61003788974523a68f5ecfb},
    publisher = {European Language Resources Association (ELRA)},
    title = {Old French Dependency Parsing: Results of Two Parsers, Analysed from a Linguistic Point of View},
    url = {http://www.uni-stuttgart.de/lingrom/stein/downloads/stein2016_old-french-dependency-parsing.pdf},
    year = 2016
    }

  • M. Sänger, U. Leser, S. Kemmerer, P. Adolphs, and R. Klinger, „SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German,“ in Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Paris, France, 2016.
    [BibTeX] [Download PDF]
    @inproceedings{Saenger2016,
    address = {Paris, France},
    author = {Sänger, Mario and Leser, Ulf and Kemmerer, Steffen and Adolphs, Peter and Klinger, Roman},
    booktitle = {Proceedings of the Tenth International Conference on Language Resources  and Evaluation (LREC 2016)},
    editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, Hélène and Moreno, Asunción and Odijk, Jan and Piperidis, Stelios},
    interhash = {41fdb24c1d5d99db98773069bc341db3},
    intrahash = {3dd632d89903d35e33eb757c65d8fe00},
    month = may,
    publisher = {European Language Resources Association (ELRA)},
    title = {SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German},
    url = {http://www.lrec-conf.org/proceedings/lrec2016/summaries/59.html},
    year = 2016
    }

  • Ö. Çetinoğlu, S. Schulz, and N. T. Vu, „Challenges of Computational Processing of Code-Switching,“ in Proceedings of EMNLP Workshop on Computational Approaches to Linguistic Code Switching (CALCS 2016) @EMNLP, Austin, Texas, USA, 2016.
    [BibTeX] [Abstract]

    This paper addresses challenges of Natural Language Processing (NLP) on non-canonical multilingual data in which two or more languages are mixed. It refers to code-switching which has become more popular in our daily life and therefore obtains an increasing amount of attention from the research community. We report our experience that covers not only core NLP tasks such as normalisation, language identification, language modelling, part-of-speech tagging and dependency parsing but also more downstream ones such as machine translation and automatic speech recognition. We highlight and discuss the key problems for each of the tasks with supporting examples from different language pairs and relevant previous work.

    @inproceedings{cetinoglu2016challanges,
    abstract = {This paper addresses challenges of Natural
    Language Processing (NLP) on non-canonical
    multilingual data in which two or more languages are mixed. It refers to code-switching
    which has become more popular in our
    daily life and therefore obtains an increasing
    amount of attention from the research community. We report our experience that covers not only core NLP tasks such as normalisation, language identification, language modelling, part-of-speech tagging and dependency
    parsing but also more downstream ones such
    as machine translation and automatic speech
    recognition. We highlight and discuss the key
    problems for each of the tasks with supporting
    examples from different language pairs and
    relevant previous work.},
    address = {Austin, Texas, USA},
    author = {Çetinoğlu, Özlem and Schulz, Sarah and Vu, Ngoc Thang},
    booktitle = {Proceedings of EMNLP Workshop on Computational Approaches to Linguistic Code Switching (CALCS 2016) @EMNLP},
    interhash = {06a3e19cd0f88c4d336ba80591d5b1fb},
    intrahash = {a7f7c93fe429132dcff932d7433004be},
    month = {November},
    title = {Challenges of Computational Processing of Code-Switching},
    year = 2016
    }

2015

  • J. Kuhn and N. Reiter, „A Plea for a Method-Driven Agenda in the Digital Humanities,“ in Proceeding of Digital Humanities 2015, Sydney, Australia, 2015.
    [BibTeX] [Download PDF]
    @inproceedings{Kuhn:2015aa,
    address = {Sydney, Australia},
    author = {Kuhn, Jonas and Reiter, Nils},
    booktitle = {{Proceeding of Digital Humanities 2015}},
    interhash = {93326f643f19af10e493bcc95d7c9fe0},
    intrahash = {9d199a743fea85a15f1f431e8ef151b0},
    month = {June},
    title = {{A Plea for a Method-Driven Agenda in the Digital Humanities}},
    url = {http://tinyurl.com/pl74co4},
    year = 2015
    }