Publications

[RSS subscription of publication list]

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,
    added-at = {2017-10-23T12:29:33.000+0200},
    author = {Kantner, Cathleen and Overbeck, Maximilian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24bc1521df114e85f6ef6b4be98c79c3e/max_overbeck},
    editor = {Puren, Marie and Lemke, Matthias},
    interhash = {69554f82aafc9724815cb78711eb503f},
    intrahash = {4bc1521df114e85f6ef6b4be98c79c3e},
    journal = {European Journal of Political Research},
    keywords = {methods myown},
    timestamp = {2017-10-25T16:27:59.000+0200},
    title = {The practical challenges of exploring 'soft' concepts through 'hard' methods},
    year = {2018, forthcoming}
    }

2018

  • F. Barth, E. Kim, S. Murr, and R. Klinger, “A Reporting Tool for Relational Visualization and Analysis of Character Mentions in Literature,” in Book of Abstracts – Digital Humanities im deutschsprachigen Raum, Cologne, Germany, 2018.
    [BibTeX] [Download PDF]
    @inproceedings{Barth2018,
    added-at = {2018-04-10T10:20:42.000+0200},
    address = {Cologne, Germany},
    author = {Barth, Florian and Kim, Evgeny and Murr, Sandra and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26481615938138e6f893643554a643052/dr.romanklinger},
    booktitle = {Book of Abstracts -- Digital Humanities im deutschsprachigen Raum},
    interhash = {2dbbe0ddd19f043739be71a8d76bb1ed},
    intrahash = {6481615938138e6f893643554a643052},
    keywords = {dh graph literature myown tool},
    month = {March},
    pdf = {http://www.romanklinger.de/publications/barth2018dhd.pdf},
    timestamp = {2018-04-10T10:20:42.000+0200},
    title = {A Reporting Tool for Relational Visualization and Analysis of Character Mentions in Literature},
    url = {http://www.romanklinger.de/publications/BarthKimMurrKlinger2018.html},
    year = 2018
    }

  • J. Beck, M. Willand, and N. Reiter, “Was Lesende denken: Assoziationen zu Büchern in Sozialen Medien,” in Digital Humanities im Deutschsprachigen Raum, Cologne, Germany, 2018.
    [BibTeX]
    @inproceedings{beck2018lesende,
    added-at = {2017-11-28T12:19:16.000+0100},
    address = {Cologne, Germany},
    author = {Beck, Jens and Willand, Marcus and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/292005757bd4a9cef076f8d37f10009cd/nilsreiter},
    booktitle = {Digital Humanities im Deutschsprachigen Raum},
    interhash = {505f72881e5553dc5a342722304a13e7},
    intrahash = {92005757bd4a9cef076f8d37f10009cd},
    keywords = {myown},
    month = feb,
    timestamp = {2017-11-28T12:19:16.000+0100},
    title = {Was Lesende denken: Assoziationen zu Büchern in Sozialen Medien },
    year = 2018
    }

  • M. Braun, R. Klinger, S. Padó, and G. Viehhauser, “Digitale Modellierung von Figurenkomplexität am Beispiel des Parzival von Wolfram von Eschenbach,” in Book of Abstracts – Digital Humanities im deutschsprachigen Raum, Cologne, Germany, 2018.
    [BibTeX] [Download PDF]
    @inproceedings{Braun2018,
    added-at = {2018-04-10T10:19:58.000+0200},
    address = {Cologne, Germany},
    author = {Braun, Manuel and Klinger, Roman and Padó, Sebastian and Viehhauser, Gabriel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2230e6dca4bfc96fec26145e258821b2c/dr.romanklinger},
    booktitle = {Book of Abstracts -- Digital Humanities im deutschsprachigen Raum},
    interhash = {17f1bdb210aabfdef695212637594854},
    intrahash = {230e6dca4bfc96fec26145e258821b2c},
    keywords = {dh literature myown},
    month = {March},
    pdf = {http://www.romanklinger.de/publications/viehhauser2018dhd.pdf},
    timestamp = {2018-05-14T12:54:20.000+0200},
    title = {{Digitale Modellierung von Figurenkomplexität am Beispiel des Parzival von Wolfram von Eschenbach}},
    url = {http://www.romanklinger.de/publications/BraunKlingerPadoViehhauser2018.html},
    year = 2018
    }

  • E. Gius, N. Reiter, J. Strötgen, and M. Willand, “SANTA: Systematische Analyse Narrativer Texte durch Annotation,” in Digital Humanities im Deutschsprachigen Raum, Cologne, Germany, 2018.
    [BibTeX]
    @inproceedings{gius2018santa,
    added-at = {2017-11-28T12:17:41.000+0100},
    address = {Cologne, Germany},
    author = {Gius, Evelyn and Reiter, Nils and Strötgen, Jannik and Willand, Marcus},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/27bb07808e85d740af7021bd158a36b83/nilsreiter},
    booktitle = {Digital Humanities im Deutschsprachigen Raum},
    interhash = {b41f9577b26d5839e512074b0e9c0348},
    intrahash = {7bb07808e85d740af7021bd158a36b83},
    keywords = {myown},
    month = feb,
    timestamp = {2017-11-28T12:17:41.000+0100},
    title = {SANTA: Systematische Analyse Narrativer Texte durch Annotation},
    year = 2018
    }

  • M. John, E. Marbach, S. Lohmann, F. Heimerl, and T. Ertl, “MultiCloud: Interactive Word Cloud Visualization for Multiple Texts,” Proceedings of Graphics Interface (2018), vol. 44, 2018.
    [BibTeX]
    @article{johnmulticloud,
    added-at = {2018-06-27T14:18:53.000+0200},
    author = {John, Markus and Marbach, Eduard and Lohmann, Steffen and Heimerl, Florian and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e34621ddb518cfb894557f38de91b22e/markusjohn},
    interhash = {19f1bd8a9014b378330f213b2272536e},
    intrahash = {e34621ddb518cfb894557f38de91b22e},
    journal = {Proceedings of Graphics Interface (2018)},
    keywords = {Analytics, Humanities, Visual Visualization,},
    timestamp = {2018-06-28T15:52:38.000+0200},
    title = {MultiCloud: Interactive Word Cloud Visualization for Multiple Texts},
    volume = 44,
    year = 2018
    }

  • C. Kantner and M. Overbeck, “Die Analyse „weicher” Konzepte mit „harten” korpuslinguistischen Methoden.,” in Computational Social Science: Die Analyse von Big Data, A. Blaette, J. Behnke, K. Schnapp, and C. Wagemann, Eds., Baden-Baden: Nomos Verlag, 2018, pp. 163-189.
    [BibTeX] [Download PDF]
    @incollection{kantner2017,
    added-at = {2017-03-03T17:22:26.000+0100},
    address = {Baden-Baden},
    author = {Kantner, Cathleen and Overbeck, Maximilian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/28d17bdf1900054bcd3f9c7f2d5aacec3/max_overbeck},
    booktitle = {Computational Social Science: Die Analyse von Big Data},
    editor = {Blaette, Andreas and Behnke, Joachim and Schnapp, Kai-Uwe and Wagemann, Claudius},
    interhash = {cb51d243b7fe28e74a2c28561d47698a},
    intrahash = {8d17bdf1900054bcd3f9c7f2d5aacec3},
    isbn = {978-3-8487-4393-3},
    keywords = {methods myown},
    pages = {163-189},
    publisher = {Nomos Verlag},
    timestamp = {2018-07-10T13:14:26.000+0200},
    title = {Die Analyse „weicher” Konzepte mit „harten” korpuslinguistischen Methoden.},
    url = {https://www.nomos-elibrary.de/10.5771/9783845286556-163/8-die-analyse-weicher-konzepte-mit-harten-korpusanalyti-schen-methoden},
    year = 2018
    }

  • J. Kim and R. Klinger, “Who Feels What and Why? An Annotated Corpus of Modern Literature of Semantic Roles in Emotions,” in Proceedings of COLING 2018, the 27th International Conference on Computational Linguistics, Santa Fe, USA, 2018.
    [BibTeX] [Download PDF]
    @inproceedings{Kim2018,
    added-at = {2018-05-16T23:53:34.000+0200},
    address = {Santa Fe, USA},
    author = {Kim, Jeremy and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2aca4021f05ef7ccfd96c43c6d2d8e319/dr.romanklinger},
    booktitle = {Proceedings of COLING 2018, the 27th International Conference on Computational Linguistics},
    interhash = {daaf381cc4f5568edeb26ec23608cbe1},
    intrahash = {aca4021f05ef7ccfd96c43c6d2d8e319},
    keywords = {corpus emotion myown nlp resource sentiment},
    month = {August},
    timestamp = {2018-06-20T23:19:02.000+0200},
    title = {Who Feels What and Why? An Annotated Corpus of Modern Literature of Semantic Roles in Emotions},
    url = {http://www.romanklinger.de/publications/kimklinger2018reman.pdf},
    year = 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,
    added-at = {2017-04-25T13:35:32.000+0200},
    address = {Wiesbaden},
    author = {Overbeck, Maximilian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e3683ff7684a3004e2085581c7d56d73/max_overbeck},
    booktitle = {Das Narrativ von der Rückkehr der Religionen},
    editor = {Zapf, Holger and Hidalgo, Oliver and Hildmann, Philipp W.},
    interhash = {34f9d96413db884b58af0b8bea0aed7c},
    intrahash = {e3683ff7684a3004e2085581c7d56d73},
    keywords = {media myown religion},
    publisher = {Springer Fachmedien Wiesbaden},
    timestamp = {2018-06-27T00:29:30.000+0200},
    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
    }

  • M. Riedl and S. Padó, “A Named Entity Recognition Shootout for German,” in Proceedings of ACL, Melbourne, Australia, 2018, p. 120–125.
    [BibTeX] [Abstract] [Download PDF]

    We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the- art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.

    @inproceedings{riedl18:_named_entit_recog_shoot_german,
    abstract = {We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the- art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.},
    added-at = {2018-04-20T21:32:58.000+0200},
    address = {Melbourne, Australia},
    author = {Riedl, Martin and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d5ab623b90f5b4eaa59adeea00a8f4f1/sp},
    booktitle = {Proceedings of ACL},
    interhash = {dd8b42bd1313f84e89f6e859676d8036},
    intrahash = {d5ab623b90f5b4eaa59adeea00a8f4f1},
    keywords = {conference myown},
    pages = {120--125},
    timestamp = {2018-07-24T20:25:11.000+0200},
    title = {A Named Entity Recognition Shootout for {German}},
    url = {http://aclweb.org/anthology/P18-2020.pdf},
    year = 2018
    }

  • S. Schulz, “The Taming of the Shrew – Non-Standard Text Processing in the Digital Humanities,” PhD Thesis, 2018. doi:http://dx.doi.org/10.18419/opus-9685
    [BibTeX] [Abstract]

    Natural language processing (NLP) has focused on the automatic processing of newspaper texts for many years. With the growing importance of text analysis in various areas such as spoken language understanding, social media processing and the interpretation of text material from the humanities, techniques and methodologies have to be reviewed and redefined since so called non-standard texts pose challenges on the lexical and syntactic level especially for machine-learning-based approaches. Automatic processing tools developed on the basis of newspaper texts show a decreased performance for texts with divergent characteristics. Digital Humanities (DH) as a field that has risen to prominence in the last decades, holds a variety of examples for this kind of texts. Thus, the computational analysis of the relationships of Shakespeare’s dramatic characters requires the adjustment of processing tools to English texts from the 16th-century in dramatic form. Likewise, the investigation of narrative perspective in Goethe’s ballads calls for methods that can handle German verse from the 18th century. In this dissertation, we put forward a methodology for NLP in a DH environment. We investigate how an interdisciplinary context in combination with specific goals within projects influences the general NLP approach. We suggest thoughtful collaboration and increased attention to the easy applicability of resulting tools as a solution for differences in the store of knowledge between project partners. Projects in DH are not only constituted by the automatic processing of texts but are usually framed by the investigation of a research question from the humanities. As a consequence, time limitations complicate the successful implementation of analysis techniques especially since the diversity of texts impairs the transferability and reusability of tools beyond a specific project. We answer to this with modular and thus easily adjustable project workflows and system architectures. Several instances serve as examples for our methodology on different levels. We discuss modular architectures that balance time-saving solutions and problem-specific implementations on the example of automatic postcorrection of the output text from an optical character recognition system. We address the problem of data diversity and low resource situations by investigating different approaches towards non-standard text processing. We examine two main techniques: text normalization and tool adjustment. Text normalization aims at the transformation of non-standard text in order to assimilate it to the standard whereas tool adjustment concentrates on the contrary direction of enabling tools to successfully handle a specific kind of text. We focus on the task of part-of-speech tagging to illustrate various approaches toward the processing of historical texts as an instance for non-standard texts. We discuss how the level of deviation from a standard form influences the performance of different methods. Our approaches shed light on the importance of data quality and quantity and emphasize the indispensability of annotations for effective machine learning. In addition, we highlight the advantages of problem-driven approaches where the purpose of a tool is clearly formulated through the research question. Another significant finding to emerge from this work is a summary of the experiences and increased knowledge through collaborative projects between computer scientists and humanists. We reflect on various aspects of the elaboration and formalization of research questions in the DH and assess the limitations and possibilities of the computational modeling of humanistic research questions. An emphasis is placed on the interplay of expert knowledge with respect to a subject of investigation and the implementation of tools for that purpose and the thereof resulting advantages such as the targeted improvement of digital methods through purposeful manual correction and error analysis. We show obstacles and chances and give prospects and directions for future development in this realm of interdisciplinary research.

    @phdthesis{schulz2018taming,
    abstract = {Natural language processing (NLP) has focused on the automatic processing of newspaper texts for many years. With the growing importance of text analysis in various areas such as spoken language understanding, social media processing and the interpretation
    of text material from the humanities, techniques and methodologies have to be reviewed and
    redefined since so called non-standard texts pose challenges on the lexical and syntactic level
    especially for machine-learning-based approaches. Automatic processing tools developed on the
    basis of newspaper texts show a decreased performance for texts with divergent characteristics.
    Digital Humanities (DH) as a field that has risen to prominence in the last decades, holds a
    variety of examples for this kind of texts. Thus, the computational analysis of the relationships of
    Shakespeare’s dramatic characters requires the adjustment of processing tools to English texts
    from the 16th-century in dramatic form. Likewise, the investigation of narrative perspective in
    Goethe’s ballads calls for methods that can handle German verse from the 18th century.
    In this dissertation, we put forward a methodology for NLP in a DH environment. We investigate
    how an interdisciplinary context in combination with specific goals within projects influences
    the general NLP approach. We suggest thoughtful collaboration and increased attention
    to the easy applicability of resulting tools as a solution for differences in the store of knowledge
    between project partners. Projects in DH are not only constituted by the automatic processing
    of texts but are usually framed by the investigation of a research question from the humanities.
    As a consequence, time limitations complicate the successful implementation of analysis techniques
    especially since the diversity of texts impairs the transferability and reusability of tools
    beyond a specific project. We answer to this with modular and thus easily adjustable project
    workflows and system architectures. Several instances serve as examples for our methodology
    on different levels. We discuss modular architectures that balance time-saving solutions and
    problem-specific implementations on the example of automatic postcorrection of the output text
    from an optical character recognition system. We address the problem of data diversity and low
    resource situations by investigating different approaches towards non-standard text processing.
    We examine two main techniques: text normalization and tool adjustment. Text normalization
    aims at the transformation of non-standard text in order to assimilate it to the standard whereas
    tool adjustment concentrates on the contrary direction of enabling tools to successfully handle
    a specific kind of text. We focus on the task of part-of-speech tagging to illustrate various approaches
    toward the processing of historical texts as an instance for non-standard texts. We
    discuss how the level of deviation from a standard form influences the performance of different
    methods. Our approaches shed light on the importance of data quality and quantity and emphasize
    the indispensability of annotations for effective machine learning. In addition, we highlight
    the advantages of problem-driven approaches where the purpose of a tool is clearly formulated
    through the research question.
    Another significant finding to emerge from this work is a summary of the experiences and
    increased knowledge through collaborative projects between computer scientists and humanists.
    We reflect on various aspects of the elaboration and formalization of research questions in the
    DH and assess the limitations and possibilities of the computational modeling of humanistic
    research questions. An emphasis is placed on the interplay of expert knowledge with respect
    to a subject of investigation and the implementation of tools for that purpose and the thereof
    resulting advantages such as the targeted improvement of digital methods through purposeful
    manual correction and error analysis. We show obstacles and chances and give prospects and
    directions for future development in this realm of interdisciplinary research.},
    added-at = {2018-05-17T09:51:58.000+0200},
    author = {Schulz, Sarah},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2cfe997d02421ef233eb04ad3a7762677/sarahschulz},
    doi = {http://dx.doi.org/10.18419/opus-9685},
    interhash = {54fb53cbe0787756293ac9494021a692},
    intrahash = {cfe997d02421ef233eb04ad3a7762677},
    keywords = {myown},
    month = {April},
    timestamp = {2018-05-18T10:29:59.000+0200},
    title = {The Taming of the Shrew - Non-Standard Text Processing in the Digital Humanities},
    year = 2018
    }

2017

  • J. Barnes, R. Klinger, and S. Schulte 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,
    added-at = {2017-07-12T23:10:54.000+0200},
    address = {Copenhagen, Denmark},
    author = {Barnes, Jeremy and Klinger, Roman and Schulte im Walde, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26006a4e2fe61c4198fe35f15d79e16ca/dr.romanklinger},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {ac69fc3da1cd095f0e25a83c9dd1237a},
    intrahash = {6006a4e2fe61c4198fe35f15d79e16ca},
    keywords = {deeplearning imported myown neural nlp sentiment},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    timestamp = {2018-05-14T12:55:15.000+0200},
    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,
    added-at = {2017-03-21T13:25:17.000+0100},
    address = { Montréal, Canada},
    author = {Barth, Florian and Murr, Sandra},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2fd9bff335fdcf70f506aa23fe9abb09c/sandramurr},
    booktitle = {Digital Humanities 2017: Conference Abstracts},
    interhash = {caf3c24165a78328628df5654513f08f},
    intrahash = {fd9bff335fdcf70f506aa23fe9abb09c},
    keywords = {myown},
    month = {August},
    timestamp = {2017-04-06T10:09:07.000+0200},
    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,
    added-at = {2017-09-30T08:19:58.000+0200},
    address = { Vancouver, Canada },
    author = {Blessing, Andre and Echelmeyer, Nora and John, Markus and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2832d1247fb039ce19e33a6bdc66c1023/nilsreiter},
    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},
    keywords = {myown},
    month = { August },
    pages = { 57-67 },
    publisher = { Association for Computational Linguistics },
    timestamp = {2017-09-30T08:19:58.000+0200},
    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,
    added-at = {2017-09-30T08:20:57.000+0200},
    address = { Wiesbaden, Germany },
    author = {Braun, Manuel and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/28bf86d58e56586037077bce0aec9138f/nilsreiter},
    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},
    keywords = {myown},
    month = { April },
    pages = { 5-20 },
    publisher = { Reichert Verlag },
    series = { Jahrbuch der Oswald von Wolkenstein-Gesellschaft },
    timestamp = {2017-09-30T08:20:57.000+0200},
    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.},
    added-at = {2017-02-21T15:50:43.000+0100},
    address = {Bern, Schwitzerland},
    author = {Echelmeyer, Nora and Reiter, Nils and Schulz, Sarah},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23d21302e42bdfbe74e0edc3fe007573c/sarahschulz},
    booktitle = {DHd 2017 Konferenzabstracts},
    description = {http://www.ims.uni-stuttgart.de/forschung/ressourcen/werkzeuge/PoS_Tag_MHG.html},
    interhash = {7d66653bf3ac0187f585987f534a25ac},
    intrahash = {3d21302e42bdfbe74e0edc3fe007573c},
    keywords = {myown},
    pages = {141 - 147},
    timestamp = {2017-02-21T16:06:49.000+0100},
    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,
    added-at = {2017-07-12T23:10:54.000+0200},
    address = {Copenhagen, Denmark},
    author = {Hartung, Matthias and Klinger, Roman and Mohme, Julian and Vogel, Lars and Schmidtke, Franziska},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2caa23eb23d1a01b39e62a9fd4bd0225c/dr.romanklinger},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {2471bf1148fb27848a4ae9f34d93534b},
    intrahash = {caa23eb23d1a01b39e62a9fd4bd0225c},
    keywords = {dh imported myown socialmedia textmining},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    timestamp = {2017-09-14T10:54:17.000+0200},
    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, p. 320–325.
    [BibTeX] [Download PDF]
    @inproceedings{Hartung2017,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Cham},
    author = {Hartung, Matthias and Klinger, Roman and Schmidtke, Franziska and Vogel, Lars},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/246d57ac77c3dfce4b682c0d0e9b1ed77/dr.romanklinger},
    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},
    keywords = {extremism hate media mining myown nlp right-wing social speech},
    pages = {320--325},
    pdf = {http://www.romanklinger.de/publications/hartung2017-NLDB-short.pdf},
    publisher = {Springer International Publishing},
    timestamp = {2017-06-13T21:19:25.000+0200},
    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.},
    added-at = {2017-03-06T16:42:45.000+0100},
    author = {Heimerl, Florian and John, Markus and Han, Qi and Koch, Steffen and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/279820e1562a3b7af96d90ebb328ba161/markusjohn},
    interhash = {d6457d13954d6aefb50c5b7ef91cfb35},
    intrahash = {79820e1562a3b7af96d90ebb328ba161},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    keywords = {analytics, document focus+context interaction mining, myown techniques, text visual visualization},
    timestamp = {2017-03-10T10:39:35.000+0100},
    title = {DocuCompass: Effective Exploration of Document Landscapes},
    year = 2017
    }

  • M. John, C. Richter, S. Koch, A. Kuczera, and T. Ertl, “Interactive Visual Exploration of the Regesta Imperii,” Digital Humanities, Montreal, Canada, August 8-11, 2017, 2017.
    [BibTeX]
    @article{johninteractive,
    added-at = {2018-02-12T15:04:02.000+0100},
    author = {John, Markus and Richter, Christian and Koch, Steffen and Kuczera, Andreas and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e85bd57d174a86079fc058c54cb81262/markusjohn},
    interhash = {41a6844ecb0d7bd18b939d5c120eddf8},
    intrahash = {e85bd57d174a86079fc058c54cb81262},
    journal = {Digital Humanities, Montreal, Canada, August 8-11, 2017},
    keywords = {Digital Humanities; Text Visualization},
    timestamp = {2018-03-07T12:13:34.000+0100},
    title = {Interactive Visual Exploration of the Regesta Imperii},
    year = 2017
    }

  • M. John, S. Koch, and T. Ertl, “Uncertainty in Visual Text Analysis in the Context of the Digital Humanities,” DESIGNING FOR UNCERTAINTY IN HCI: WHEN DOES UNCERTAINTY HELP? Workshop on CHI 2017, Denver, Colorado, 2017.
    [BibTeX]
    @article{markusjohnsteffenkoch2017uncertainty,
    added-at = {2018-02-12T14:55:50.000+0100},
    author = {John, Markus and Koch, Steffen and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2122a6eea056993aef9aa9e4ea3017471/markusjohn},
    interhash = {4a6fed5f34a2b0c11662001a3682fa8b},
    intrahash = {122a6eea056993aef9aa9e4ea3017471},
    journal = {DESIGNING FOR UNCERTAINTY IN HCI: WHEN DOES UNCERTAINTY HELP? Workshop on CHI 2017, Denver, Colorado},
    keywords = {Digital Humanities},
    timestamp = {2018-06-27T14:09:48.000+0200},
    title = {Uncertainty in Visual Text Analysis in the Context of the Digital Humanities},
    year = 2017
    }

  • M. John, K. Kurzhals, S. Koch, and D. Weiskopf, “A Visual Analytics Approach for Semantic Multi-Video Annotation,” , 2017.
    [BibTeX]
    @article{johnvisual,
    added-at = {2018-02-12T14:50:38.000+0100},
    author = {John, Markus and Kurzhals, Kuno and Koch, Steffen and Weiskopf, Daniel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c15cdea0c6cf2b5905b9856d8f19a0c7/markusjohn},
    interhash = {0de674c3c3848876fdd9f697aa67978c},
    intrahash = {c15cdea0c6cf2b5905b9856d8f19a0c7},
    keywords = {Visual analysis digital},
    timestamp = {2018-02-19T12:48:10.000+0100},
    title = {A Visual Analytics Approach for Semantic Multi-Video Annotation},
    year = 2017
    }

  • M. John, S. Lohmann, S. Koch, M. Wörner, and T. Ertl, “Visual Analysis of Character and Plot Information Extracted from Narrative Text,” in Computer Vision, Imaging and Computer Graphics Theory and Applications, Cham, 2017, p. 220–241.
    [BibTeX] [Abstract]

    The study of novels and the analysis of their plot, characters and other information entities are complex and time-consuming 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 field of computational linguistics can be used to automatically extract entities and their relations from digitized novels. However, these methods have known limitations, especially when applied to narrative text that does often not follow a common schema but can have various forms. Visualizations can address the limitations by providing visual clues to show the uncertainty of the extracted information, so that literary scholars get a better idea of the accuracy of the methods. In addition, interaction can be used to let users control and adapt the extraction and visualization methods according to their needs. This paper presents ViTA, 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. Furthermore, the paper discusses how uncertainty might be represented in the different views and how users can be enabled to adapt the automatic methods.

    @inproceedings{10.1007/978-3-319-64870-5_11,
    abstract = {The study of novels and the analysis of their plot, characters and other information entities are complex and time-consuming 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 field of computational linguistics can be used to automatically extract entities and their relations from digitized novels. However, these methods have known limitations, especially when applied to narrative text that does often not follow a common schema but can have various forms. Visualizations can address the limitations by providing visual clues to show the uncertainty of the extracted information, so that literary scholars get a better idea of the accuracy of the methods. In addition, interaction can be used to let users control and adapt the extraction and visualization methods according to their needs. This paper presents ViTA, 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. Furthermore, the paper discusses how uncertainty might be represented in the different views and how users can be enabled to adapt the automatic methods.},
    added-at = {2018-02-12T15:00:59.000+0100},
    address = {Cham},
    author = {John, Markus and Lohmann, Steffen and Koch, Steffen and W{\"o}rner, Michael and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2165cbdc68a3b67c55a4a5e3d4896845e/markusjohn},
    booktitle = {Computer Vision, Imaging and Computer Graphics Theory and Applications},
    editor = {Braz, Jos{\'e} and Magnenat-Thalmann, Nadia and Richard, Paul and Linsen, Lars and Telea, Alexandru and Battiato, Sebastiano and Imai, Francisco},
    interhash = {75cbfc1fa1c7957b01d7a88d2c9aa6c7},
    intrahash = {165cbdc68a3b67c55a4a5e3d4896845e},
    isbn = {978-3-319-64870-5},
    keywords = {Visualization},
    pages = {220--241},
    publisher = {Springer International Publishing},
    timestamp = {2018-03-07T12:10:59.000+0100},
    title = {Visual Analysis of Character and Plot Information Extracted from Narrative Text},
    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,
    added-at = {2017-06-09T21:10:16.000+0200},
    author = {Kim, Evgeny and Padó, Sebastian and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e019f211e00b14784038b55e89383254/dr.romanklinger},
    booktitle = {Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL)},
    interhash = {f52f46a8c49486fc8960fa67bd6e0c11},
    intrahash = {e019f211e00b14784038b55e89383254},
    keywords = {myown},
    organization = {Association for Computational Linguistics},
    pdf = {http://www.romanklinger.de/publications/kim2017a.pdf},
    timestamp = {2018-05-14T19:55:29.000+0200},
    title = {Investigating the Relationship between Literary Genres and Emotional Plot Development},
    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,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Montréal, Canada},
    author = {Kim, Evgeny and Padó, Sebastian and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a067a8ffd2c65b5f5718dd9e6fc90178/dr.romanklinger},
    booktitle = {Digital Humanities 2017: Conference Abstracts},
    interhash = {1b6975f7865deb345eb953fea2f88a61},
    intrahash = {a067a8ffd2c65b5f5718dd9e6fc90178},
    keywords = {analysis dh emotion literature myown},
    month = {August},
    note = {accepted},
    organization = {McGill University and Universit\'e de Montr\'eal},
    pdf = {http://www.romanklinger.de/publications/kim2017.pdf},
    timestamp = {2017-04-27T23:15:16.000+0200},
    title = {Prototypical Emotion Developments in Literary Genres},
    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, p. 313–319.
    [BibTeX] [Download PDF]
    @inproceedings{Klinger2017,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Cham},
    author = {Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/211363b658eef4d5ee66cf8b13df05277/dr.romanklinger},
    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},
    keywords = {caption classification emotion generation myown ocr},
    pages = {313--319},
    pdf = {http://www.romanklinger.de/publications/klinger2017-nldb.pdf},
    publisher = {Springer International Publishing},
    timestamp = {2017-06-13T21:23:16.000+0200},
    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.},
    added-at = {2017-03-06T17:17:40.000+0100},
    author = {Kurzhals, Kuno and John, Markus and Heimerl, Florian and Kuznecov, Paul and Weiskop, Daniel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/231c5727eb88426afb28ed3dd780d71bc/markusjohn},
    booktitle = {IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 18},
    interhash = {b5d426101d290c9be0f34bb94afa732c},
    intrahash = {31c5727eb88426afb28ed3dd780d71bc},
    keywords = {Movie analysis, analytics myown video visual visualization,},
    pages = 51,
    timestamp = {2017-03-10T10:38:39.000+0100},
    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,
    added-at = {2017-07-12T23:10:54.000+0200},
    address = {Copenhagen, Denmark},
    author = {K\"oper, Maximilian and Kim, Evgeny and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2633fcb7560b743251a73b99fcd8617c4/dr.romanklinger},
    booktitle = {Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {21cc4e2239a9bfcb2d880d865e7400b9},
    intrahash = {633fcb7560b743251a73b99fcd8617c4},
    keywords = {emotion imported myown nlp sentiment},
    organization = {Workshop at Conference on Empirical Methods in Natural Language Processing},
    publisher = {Association for Computational Linguistics},
    timestamp = {2017-09-14T10:53:44.000+0200},
    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, 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,
    added-at = {2017-09-30T08:17:26.000+0200},
    address = { Chemnitz, Germany },
    author = {Reiter, Nils and Kuhn, Jonas and Willand, Marcus},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2586d900175fc399e7f7e8a666770849d/nilsreiter},
    booktitle = { INFORMATIK 2017 },
    doi = {10.18420/in2017_119},
    editor = {Eibl, Maximilian and Gaedke, Martin},
    interhash = {386b69fa2beeaf379a07f1f655aaf883},
    intrahash = {586d900175fc399e7f7e8a666770849d},
    isbn = {978-3-88579-669-5},
    keywords = {collaboration digital-humanities gui myown user-interface},
    month = { September },
    pages = { 1179-1184 },
    publisher = { Gesellschaft für Informatik e.V. },
    series = { Lecture Notes in Informatics (LNI) },
    timestamp = {2017-09-30T08:17:26.000+0200},
    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,
    added-at = {2017-03-20T09:05:43.000+0100},
    address = { Montreal, Canada },
    author = {Reiter, Nils and Gius, Evelyn and Strötgen, Jannik and Willand, Marcus},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/292eb79bf73357b1b687008f0a0f4f35a/nilsreiter},
    booktitle = { Digital Humanities 2017: Conference Abstracts },
    interhash = {1c650a67e135cbefcddbf25f6b5c3c29},
    intrahash = {92eb79bf73357b1b687008f0a0f4f35a},
    keywords = {myown},
    month = {August},
    note = {accepted},
    timestamp = {2017-03-20T09:10:33.000+0100},
    title = { A Shared Task for a Shared Goal - Systematic Annotation of Literary Texts },
    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,
    added-at = {2017-09-14T10:56:15.000+0200},
    author = {Reiter, Nils and Schulz, Sarah and Kremer, Gerhard and Klinger, Roman and Viehhauser, Gabriel and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20fa2d6c1246dfa5403998794243ca148/dr.romanklinger},
    booktitle = {Proceedings of the GSCL Workshop on Teaching NLP for Digital Humanities (Teach4DH 2017)},
    interhash = {383ce9948347f0cba3dc027823047aab},
    intrahash = {0fa2d6c1246dfa5403998794243ca148},
    keywords = {dh digitalhumanities myown nlp teaching},
    pdf = {http://www.romanklinger.de/publications/teach4dhpaper2017.pdf},
    timestamp = {2017-09-14T20:27:42.000+0200},
    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
    }

  • 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 EMNLP WASSA workshop, Copenhagen, Denmark, 2017.
    [BibTeX] [Abstract] [Download PDF]

    There is a rich variety of data sets for sentiment analysis (viz., polarity and subjectivity classification). For the more challenging task of detecting discrete emotions following the definitions of Ekman and Plutchik, however, there are much fewer data sets, and notably no resources for the social media domain. This paper contributes to closing this gap by extending the SemEval 2016 stance and sentiment dataset with emotion annotation. We (a) analyse annotation reliability and annotation merging; (b) investigate the relation between emotion annotation and the other annotation layers (stance, sentiment); (c) report modelling results as a baseline for future work.

    @inproceedings{schuff17:_annot_model_and_analy_of,
    abstract = {There is a rich variety of data sets for sentiment analysis (viz., polarity and subjectivity classification). For the more challenging task of detecting discrete emotions following the definitions of Ekman and Plutchik, however, there are much fewer data sets, and notably no resources for the social media domain. This paper contributes to closing this gap by extending the SemEval 2016 stance and sentiment dataset with emotion annotation. We (a) analyse annotation reliability and annotation merging; (b) investigate the relation between emotion annotation and the other annotation layers (stance, sentiment); (c) report modelling results as a baseline for future work.},
    added-at = {2017-07-14T21:42:12.000+0200},
    address = {Copenhagen, Denmark},
    author = {Schuff, Hendrik and Barnes, Jeremy and Mohme, Julian and Padó, Sebastian and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c6f61025624b3cbfb5f3a4ae2b0b47a4/sp},
    booktitle = {Proceedings of the EMNLP WASSA workshop},
    interhash = {b86da90b5498bf4348d070bf270368e8},
    intrahash = {c6f61025624b3cbfb5f3a4ae2b0b47a4},
    keywords = {myown workshop},
    timestamp = {2017-11-22T17:19:39.000+0100},
    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, p. 3–14.
    [BibTeX] [Download PDF]
    @inproceedings{Saenger2017,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Cham},
    author = {Sänger, Mario and Leser, Ulf and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26c4ac476a2427f91a766742356068e69/dr.romanklinger},
    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},
    keywords = {app myown reviews sentiment},
    pages = {3--14},
    pdf = {http://www.romanklinger.de/publications/saenger2017-nldb.pdf},
    publisher = {Springer International Publishing},
    timestamp = {2017-06-13T21:22:44.000+0200},
    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
    }

  • G. Viehhauser and F. Barth, “Digitale Modellierung literarischen Raums,” in Dhd Bern 2017. Digitale Nachhaltigkeit. Konferenzabstracts. Universität Bern 13. – 18. Februar 2017, 2017, pp. 128-132.
    [BibTeX] [Download PDF]
    @inproceedings{viehhauser2017digitale,
    added-at = {2018-03-15T11:11:41.000+0100},
    author = {Viehhauser, Gabriel and Barth, Florian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/281a495df14ace821eef41e00cd73563f/viehhauser},
    booktitle = {Dhd Bern 2017. Digitale Nachhaltigkeit. Konferenzabstracts. Universität Bern 13. – 18. Februar 2017},
    interhash = {3a33a402427ed7ba879255d6504bc074},
    intrahash = {81a495df14ace821eef41e00cd73563f},
    keywords = {digitalhumanities literaturwissenschaft myown narratology space spatialHumanities},
    pages = {128-132},
    timestamp = {2018-03-15T11:11:41.000+0100},
    title = {Digitale Modellierung literarischen Raums},
    url = {http://www.dhd2017.ch/wp-content/uploads/2017/03/Abstractband_def3_M%C3%A4rz.pdf},
    year = 2017
    }

  • G. Viehhauser, “Digitale Gattungsgeschichten. Minnesang zwischen generischer Konstanz und Wende,” Zeitschrift für digitale Geisteswissenschaften, 2017. doi:10.17175/2017_003
    [BibTeX] [Abstract]

    Digitale Analysen literarischer Gattungen gehen häufig davon aus, dass sich Gattungen anhand konstant bleibender Features identifizieren lassen. Gattungen können jedoch immer auch als geschichtliche Verlaufsformen mit historisch veränderlichen Features rekonstruiert werden. Der Beitrag möchte exemplarisch anhand eines prominenten Beispiels aus der mittelhochdeutschen Literatur, nämlich des Minnesangs, aufzeigen, wie und dass sich gattungsgeschichtliche Entwicklungen mit digitalen Methoden nachzeichnen lassen. Mit Hilfe von Frequenzanalysen und Topic Modeling soll der in der Forschung viel diskutierten Frage nachgegangen werden, ob es im Verlauf des Minnesangs zu einer gattungsgeschichtlichen Wende kam, die die Lyrik der Spätzeit vom ›klassischen‹ Sang unterscheidet. Digital analyses of literary genres are often based on the assumption that genres can be identified through constant and unvarying features. However, genres always reveal themselves as historically-based constructs with features that change and evolve over time. This paper illustrates how such historical developments in genres can be retraced with digital methods by means of a prominent example from Middle High German literature, Minnesang. With the help of frequency analysis and topic modeling, a research question which has been much debated will be discussed: whether there was an historical shift in genre during the development of Minnesang that differentiates the lyric poetry of the later period from ›classical‹ Sang.

    @article{viehhauser2017digitale,
    abstract = {Digitale Analysen literarischer Gattungen gehen häufig davon aus, dass sich Gattungen anhand konstant bleibender Features identifizieren lassen. Gattungen können jedoch immer auch als geschichtliche Verlaufsformen mit historisch veränderlichen Features rekonstruiert werden. Der Beitrag möchte exemplarisch anhand eines prominenten Beispiels aus der mittelhochdeutschen Literatur, nämlich des Minnesangs, aufzeigen, wie und dass sich gattungsgeschichtliche Entwicklungen mit digitalen Methoden nachzeichnen lassen. Mit Hilfe von Frequenzanalysen und Topic Modeling soll der in der Forschung viel diskutierten Frage nachgegangen werden, ob es im Verlauf des Minnesangs zu einer gattungsgeschichtlichen Wende kam, die die Lyrik der Spätzeit vom ›klassischen‹ Sang unterscheidet.
    Digital analyses of literary genres are often based on the assumption that genres can be identified through constant and unvarying features. However, genres always reveal themselves as historically-based constructs with features that change and evolve over time. This paper illustrates how such historical developments in genres can be retraced with digital methods by means of a prominent example from Middle High German literature, Minnesang. With the help of frequency analysis and topic modeling, a research question which has been much debated will be discussed: whether there was an historical shift in genre during the development of Minnesang that differentiates the lyric poetry of the later period from ›classical‹ Sang.
    },
    added-at = {2018-03-15T10:14:41.000+0100},
    author = {Viehhauser, Gabriel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/281c79603014cb4a2a6fa1efd6be1648c/viehhauser},
    doi = {10.17175/2017_003},
    interhash = {bbc7484fb31668463e2e2daf55a7902d},
    intrahash = {81c79603014cb4a2a6fa1efd6be1648c},
    journal = {Zeitschrift für digitale Geisteswissenschaften},
    keywords = {digitalhumanities genre literaturwissenschaft minnesang mittelhochdeutsch myown},
    timestamp = {2018-03-15T14:08:58.000+0100},
    title = {Digitale Gattungsgeschichten. Minnesang zwischen generischer Konstanz und Wende},
    year = 2017
    }

  • G. Viehhauser and F. Barth, “Towards a Digital Narratology of Space,” in Digital Humanities 2017. Conference Abstracts. McGill University & Université de Montréal. Montréal, Canada. August 8-11, 2017, 2017, pp. 643-646.
    [BibTeX] [Download PDF]
    @inproceedings{viehhauser2017towards,
    added-at = {2018-03-15T10:40:27.000+0100},
    author = {Viehhauser, Gabriel and Barth, Florian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25ec77d28c0ac1280bf78f15c67b4c41e/viehhauser},
    booktitle = {Digital Humanities 2017. Conference Abstracts. McGill University & Université de Montréal. Montréal, Canada. August 8-11, 2017},
    interhash = {d24c3ddde0dd61d6b0e248135a1faf9a},
    intrahash = {5ec77d28c0ac1280bf78f15c67b4c41e},
    keywords = {digitalhumanities literaturwissenschaft myown narratology space},
    pages = {643-646},
    timestamp = {2018-03-15T10:41:52.000+0100},
    title = {Towards a Digital Narratology of Space},
    url = {https://dh2017.adho.org/abstracts/DH2017-abstracts.pdf},
    year = 2017
    }

  • G. Viehhauser, R. Kirstein, F. Barth, and A. Pairamidis, “Cadmus and the Cow: A Digital Narratology of Space in Ovid’s Metamorphoses,” in Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017), P. Fogliaroni, A. Ballatore, and E. Clementini, Eds., Cham: Springer, 2017, pp. 293-301. doi:10.1007/978-3-319-63946-8
    [BibTeX]
    @incollection{viehhauser2017cadmus,
    added-at = {2018-03-15T10:36:56.000+0100},
    address = {Cham},
    author = {Viehhauser, Gabriel and Kirstein, Robert and Barth, Florian and Pairamidis, Andreas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/288ad9c3e2882d8a1058694b14e833bbc/viehhauser},
    booktitle = {Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017)},
    doi = {10.1007/978-3-319-63946-8},
    editor = {Fogliaroni, Paolo and Ballatore, Andrea and Clementini, Eliseo},
    interhash = {12c309e4948ca71bf5c6e529bde69aed},
    intrahash = {88ad9c3e2882d8a1058694b14e833bbc},
    isbn = {978-3-319-63946-8},
    keywords = {Ovid digitalhumanities myown narratology networkAnalysis space spatialHumanities},
    pages = { 293-301},
    publisher = {Springer},
    timestamp = {2018-03-15T11:24:50.000+0100},
    title = {Cadmus and the Cow: A Digital Narratology of Space in Ovid's Metamorphoses},
    year = 2017
    }

  • G. Viehhauser, “Philologie und Phylogenese. Interdisziplinäre Berührungspunkte zwischen Biologie und Germanistik,” in Mittelalterphilologien heute. Eine Standortbestimmung, A. Molinari and M. Dallapiazza, Eds., Würzburg: Königshausen und Neumann, 2017, vol. 1, pp. 245-264.
    [BibTeX]
    @incollection{viehhauser2017philologie,
    added-at = {2018-03-15T11:15:04.000+0100},
    address = {Würzburg},
    author = {Viehhauser, Gabriel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2fabf664bdb6552affb9d3d48a1fac02e/viehhauser},
    booktitle = {Mittelalterphilologien heute. Eine Standortbestimmung},
    editor = {Molinari, Alesandra and Dallapiazza, Michael},
    interhash = {919a1eed2f7d45264cf4a29c3d550f6d},
    intrahash = {fabf664bdb6552affb9d3d48a1fac02e},
    keywords = {Parzival digitalhumanities myown pyhlogenetics stemmatology},
    pages = {245-264},
    publisher = {Königshausen und Neumann},
    timestamp = {2018-03-15T11:23:18.000+0100},
    title = {Philologie und Phylogenese. Interdisziplinäre Berührungspunkte zwischen Biologie und Germanistik},
    volume = 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,
    added-at = {2017-09-30T08:14:35.000+0200},
    address = { Stuttgart, Germany },
    author = {Willand, Marcus and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e439e03ae5d7ab58d3e436fb223e3bbe/nilsreiter},
    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},
    keywords = {Drama Gattung Geschlecht Kleist digital-humanities myown},
    month = { September },
    pages = { 142-160 },
    publisher = { J.B. Metzler },
    series = { Kleist-Jahrbuch },
    timestamp = {2017-09-30T08:14:35.000+0200},
    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.},
    added-at = {2016-08-26T07:09:54.000+0200},
    address = {Jagiellonian University \& Pedagogical University, Krak{\'o}w},
    author = {Blessing, Andre and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/245b7812a28f0e562934041ac14947f9f/nilsreiter},
    booktitle = {Digital Humanities 2016: Conference Abstracts},
    interhash = {c27db04362a3f04c64a95731d7c95c1b},
    intrahash = {45b7812a28f0e562934041ac14947f9f},
    keywords = {creta crosslingual emigration},
    pages = {744-745},
    timestamp = {2016-08-26T07:09:54.000+0200},
    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.},
    added-at = {2017-03-06T17:30:07.000+0100},
    author = {El-Assady, Mennatallah and Gold, Valentin and John, Markus and Ertl, Thomas and Keim, Daniel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26784079c89f2d42527d30c9ddd81ff56/markusjohn},
    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},
    keywords = {Close Digital Distant Humanities, Reading Reading, Text Visualization, myown},
    timestamp = {2017-03-10T10:37:51.000+0100},
    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,
    added-at = {2017-03-09T14:15:43.000+0100},
    author = {Heyer, Gerhard and Kantner, Cathleen and Niekler, Andreas and Overbeck, Maximilian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c1bc0d432b83dfdb869109b35c96f813/max_overbeck},
    booktitle = {Proceedings of the 12th International conference on Terminology and Knowledge Engineering (TKE 2016)},
    interhash = {dd3836d7818f4d9dd331fd3da5f45f45},
    intrahash = {c1bc0d432b83dfdb869109b35c96f813},
    keywords = {methods myown},
    timestamp = {2017-03-09T14:15:43.000+0100},
    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.},
    added-at = {2017-03-06T17:10:42.000+0100},
    author = {John, Markus and Lohmann, Steffen and Koch, Steffen and Wörner, Michael and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2b1f872da093bff4f949ba42c67bfb1b0/markusjohn},
    interhash = {2d94ee951b425ccdc4c9dad2787b8042},
    intrahash = {b1f872da093bff4f949ba42c67bfb1b0},
    journal = {In Proceedings of the 6th International Conference on Information Visualization Theory and Applications},
    keywords = {Analytics, Close Digital Distant Humanities, Reading Text Visual Visualization, myown},
    timestamp = {2017-03-10T10:39:02.000+0100},
    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,
    added-at = {2017-03-09T14:17:37.000+0100},
    author = {Kantner, Cathleen and Kuhn, Jonas and Blessing, Andre and Overbeck, Maximilian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29bb37edbb6fd8b29aa03025186c54c87/max_overbeck},
    booktitle = {Jahrestagung der Digital Humanities im deutschsprachigen Raum (DHd)},
    interhash = {54c41b9ae544e537c6eda47c449d6be2},
    intrahash = {9bb37edbb6fd8b29aa03025186c54c87},
    keywords = {methods myown},
    timestamp = {2017-03-09T14:17:37.000+0100},
    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” and “Amerika”,” in Digital Humanities 2016: Conference Abstracts, Kraków, Poland, 2016, p. 826–828.
    [BibTeX] [Download PDF]
    @inproceedings{Klinger2016,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Krak\'ow, Poland},
    author = {Klinger, Roman and Suliya, Surayya Samat and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2521aaec63f1fc7bd58d6568750070eba/dr.romanklinger},
    booktitle = {Digital Humanities 2016: Conference Abstracts},
    interhash = {f31473c37c8ba97062910c7d4bb2590c},
    intrahash = {521aaec63f1fc7bd58d6568750070eba},
    keywords = {analysis emotion literature myown},
    month = {July},
    organization = {Jagiellonian University and Pedagogical University},
    pages = {826--828},
    timestamp = {2017-04-27T23:15:00.000+0200},
    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,
    added-at = {2016-02-29T15:23:31.000+0100},
    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},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2cad8e439eb38f7e41548e99fe223523e/nilsreiter},
    booktitle = {Proceedings of DHd},
    interhash = {5ec0e3be951b3aa031535222f127f0a2},
    intrahash = {cad8e439eb38f7e41548e99fe223523e},
    keywords = {cretapubs},
    month = {March},
    timestamp = {2016-02-29T16:44:26.000+0100},
    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, p. 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.},
    added-at = {2016-08-26T07:13:52.000+0200},
    address = {Berlin, Germany},
    author = {Le, Dieu-Thu and Vu, Ngoc Thang and Blessing, Andre},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25f8ec62ef3cc56dce5b2a5da6a2c5ba1/nilsreiter},
    booktitle = {Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities},
    interhash = {a9fe53c22c939f4f35eeb96281c3aa09},
    intrahash = {5f8ec62ef3cc56dce5b2a5da6a2c5ba1},
    keywords = {creta},
    month = {August},
    pages = {134--139},
    publisher = {Association for Computational Linguistics},
    timestamp = {2016-08-26T07:13:52.000+0200},
    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, p. 203–216.
    [BibTeX] [Download PDF]
    @inproceedings{Ling2016,
    added-at = {2017-03-31T18:24:06.000+0200},
    author = {Ling, Jennifer and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a565f08265f08e955343158dd7a88b9b/dr.romanklinger},
    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},
    keywords = {classification imported irony media myown nlp sarcasm social},
    pages = {203--216},
    pdf = {http://www.romanklinger.de/publications/ling2016.pdf},
    publisher = {Springer International Publishing},
    series = {Lecture Notes in Computer Science},
    timestamp = {2017-04-27T23:15:13.000+0200},
    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,
    added-at = {2018-04-10T14:41:59.000+0200},
    author = {Rösiger, Ina and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c2d625e7ccc3caa20e0a39db90af082c/creta},
    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 = {c2d625e7ccc3caa20e0a39db90af082c},
    keywords = {copied from:drgerhardkremer},
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2018-04-10T14:41:59.000+0200},
    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, p. 1736–1745.
    [BibTeX] [Download PDF]
    @inproceedings{Scheible2016,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Berlin, Germany},
    author = {Scheible, Christian and Klinger, Roman and Pad\'{o}, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2b0b55f48c4f762fa4e0f0bcc79960395/dr.romanklinger},
    booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
    interhash = {63a2139132dde0b43f5709271ec735c0},
    intrahash = {b0b55f48c4f762fa4e0f0bcc79960395},
    keywords = {imported models myown nlp quotations},
    month = {August},
    pages = {1736--1745},
    publisher = {Association for Computational Linguistics},
    timestamp = {2017-04-27T23:15:08.000+0200},
    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.},
    added-at = {2016-09-21T15:22:50.000+0200},
    address = {Krakau},
    author = {Schulz, Sarah and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/216bf2bc8a8a1dd6f6f38f87601004bec/sarahschulz},
    booktitle = {Proceeding of Digital Humanities 2016},
    interhash = {8612c781ea6516fe4f1c7c96d7f019e6},
    intrahash = {16bf2bc8a8a1dd6f6f38f87601004bec},
    keywords = {attribution authorship evaluation method myown},
    month = {July},
    pages = {883-885},
    timestamp = {2016-09-21T15:56:48.000+0200},
    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, p. 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.
    },
    added-at = {2016-08-26T07:00:44.000+0200},
    address = {Berlin, Germany},
    author = {Schulz, Sarah and Keller, Mareike},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/21e67f2505fd63a46d1ea35989927f23c/nilsreiter},
    booktitle = {Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities},
    interhash = {254d03475681d83d705b2c849f9a33ef},
    intrahash = {1e67f2505fd63a46d1ea35989927f23c},
    keywords = {code-switching},
    month = {August},
    pages = {43--51},
    publisher = {Association for Computational Linguistics},
    timestamp = {2016-08-26T07:02:15.000+0200},
    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.},
    added-at = {2016-06-08T13:12:46.000+0200},
    address = {Slovenia},
    author = {Schulz, Sarah and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d8e04f51ca5cc496f20cf534ef8ebe4d/sarahschulz},
    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},
    keywords = {Historical PoS Tagging Text languages low-resource myown},
    month = may,
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2016-06-15T15:28:54.000+0200},
    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,
    added-at = {2017-09-30T08:40:21.000+0200},
    address = {Portoroz, Slovenia},
    author = {Stein, Achim},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2f1167834b61003788974523a68f5ecfb/nilsreiter},
    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},
    keywords = {Parsing},
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2017-09-30T08:40:21.000+0200},
    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,
    added-at = {2017-03-31T18:24:06.000+0200},
    address = {Paris, France},
    author = {Sänger, Mario and Leser, Ulf and Kemmerer, Steffen and Adolphs, Peter and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23dd632d89903d35e33eb757c65d8fe00/dr.romanklinger},
    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},
    keywords = {annotations app corpus myown resource reviews sentiment},
    month = may,
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2017-04-27T23:15:05.000+0200},
    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.},
    added-at = {2016-09-21T15:32:03.000+0200},
    address = {Austin, Texas, USA},
    author = {Çetinoğlu, Özlem and Schulz, Sarah and Vu, Ngoc Thang},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a7f7c93fe429132dcff932d7433004be/sarahschulz},
    booktitle = {Proceedings of EMNLP Workshop on Computational Approaches to Linguistic Code Switching (CALCS 2016) @EMNLP},
    interhash = {06a3e19cd0f88c4d336ba80591d5b1fb},
    intrahash = {a7f7c93fe429132dcff932d7433004be},
    keywords = {myown},
    month = {November},
    timestamp = {2016-12-14T15:43:01.000+0100},
    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,
    added-at = {2016-02-09T12:02:53.000+0100},
    address = {Sydney, Australia},
    author = {Kuhn, Jonas and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29d199a743fea85a15f1f431e8ef151b0/nilsreiter},
    booktitle = {{Proceeding of Digital Humanities 2015}},
    interhash = {93326f643f19af10e493bcc95d7c9fe0},
    intrahash = {9d199a743fea85a15f1f431e8ef151b0},
    keywords = {creta cretapubs},
    month = {June},
    timestamp = {2016-02-29T16:33:04.000+0100},
    title = {{A Plea for a Method-Driven Agenda in the Digital Humanities}},
    url = {http://tinyurl.com/pl74co4},
    year = 2015
    }