Publications

[RSS subscription of publication list]

2022

  • S. Padó and D. Hole, “Distributional Analysis of Polysemous Function Words,” , 2022.
    [BibTeX] [Download PDF]
    @preprint{hole19:_distr_analy_funct_words,
    added-at = {2019-06-04T09:28:34.000+0200},
    address = {Batumi, Georgia},
    author = {Padó, Sebastian and Hole, Daniel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2385793c2231d56c77badfa1b331614ef/sp},
    booktitle = {Proceedings of the 13th International Tbilisi Symposium on Language, Logic and Computation. (In press.)},
    interhash = {2037390fcf19e0af578910bcf7d27a0e},
    intrahash = {385793c2231d56c77badfa1b331614ef},
    keywords = {myown preprint},
    note = {To appear in Proceedings of the 13th International Tbilisi Symposium on Language, Logic and Computation},
    timestamp = {2022-01-28T15:44:53.000+0100},
    title = {Distributional Analysis of Polysemous Function Words},
    url = {https://arxiv.org/abs/1907.10449},
    year = 2022
    }

2021

  • F. Casel, A. Heindl, and R. Klinger, “Emotion Recognition under Consideration of the Emotion Component Process Model,” in Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021), Düsseldorf, Germany, 2021, p. 49–61.
    [BibTeX] [Download PDF]
    @inproceedings{casel-etal-2021-emotion,
    added-at = {2021-10-11T14:33:23.000+0200},
    address = {D{\"u}sseldorf, Germany},
    author = {Casel, Felix and Heindl, Amelie and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e96ea74350569b28b52884c65c987c15/dr.romanklinger},
    booktitle = {Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)},
    interhash = {1200def1c4a0273d5cee19a032f2cbc6},
    intrahash = {e96ea74350569b28b52884c65c987c15},
    keywords = {nlp myown emotion},
    pages = {49--61},
    publisher = {KONVENS 2021 Organizers},
    timestamp = {2021-10-11T14:33:23.000+0200},
    title = {Emotion Recognition under Consideration of the Emotion Component Process Model},
    url = {https://aclanthology.org/2021.konvens-1.5},
    year = 2021
    }

  • E. Dayanik, A. Blessing, N. Blokker, S. Haunss, J. Kuhn, G. Lapesa, and S. Padó, “Using Hierarchical Class Structure to Improve Fine-Grained Claim Classification,” in Proceedings of the ACL Workshop of Structured Prediction, Bangkok, Thailand, 2021.
    [BibTeX] [Download PDF]
    @inproceedings{dayanik21:_using_hierar_class_struc_improv,
    added-at = {2021-06-01T20:41:13.000+0200},
    address = {Bangkok, Thailand},
    author = {Dayanik, Erenay and Blessing, Andre and Blokker, Nico and Haunss, Sebastian and Kuhn, Jonas and Lapesa, Gabriella and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20f6d2fc4aa639e7210990201291d5a5c/sp},
    booktitle = {Proceedings of the ACL Workshop of Structured Prediction},
    interhash = {dd2830015fb7948b28906be22cd03a64},
    intrahash = {0f6d2fc4aa639e7210990201291d5a5c},
    keywords = {myown workshop},
    timestamp = {2021-08-05T19:17:39.000+0200},
    title = {Using Hierarchical Class Structure to Improve Fine-Grained Claim Classification},
    url = {https://aclanthology.org/2021.spnlp-1.6/},
    year = 2021
    }

  • L. Grimminger and R. Klinger, “Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection,” in Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 2021.
    [BibTeX] [Download PDF]
    @inproceedings{Grimminger2021,
    added-at = {2021-03-04T19:47:08.000+0100},
    author = {Grimminger, Lara and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25848ea9529e158a453b3cfd39daaeab3/dr.romanklinger},
    booktitle = {Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {fe0e78194328d7d91a6fbf00d63fda23},
    intrahash = {5848ea9529e158a453b3cfd39daaeab3},
    keywords = {sentiment nlp imported myown offensivelanguage stance hatespeech},
    pdf = {http://www.romanklinger.de/publications/GrimmingerKlingerWASSA2021.pdf},
    timestamp = {2021-04-26T15:28:44.000+0200},
    title = {Hate Towards the Political Opponent: A Twitter
    Corpus Study of the 2020 US Elections on the Basis
    of Offensive Speech and Stance Detection},
    url = {https://www.aclweb.org/anthology/2021.wassa-1.18/},
    year = 2021
    }

  • J. Hofmann, E. Troiano, and R. Klinger, “Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations,” in Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 2021.
    [BibTeX] [Download PDF]
    @inproceedings{Hofmann2021,
    added-at = {2021-03-04T19:47:08.000+0100},
    author = {Hofmann, Jan and Troiano, Enrica and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2676f4758a13d201343e6a7ed539356ec/dr.romanklinger},
    booktitle = {Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {55bc218262c58d138c327926c6440688},
    intrahash = {676f4758a13d201343e6a7ed539356ec},
    keywords = {nlp imported myown emotion},
    pdf = {http://www.romanklinger.de/publications/HofmannTroianoKlingerWASSA2021.pdf},
    timestamp = {2021-04-26T15:28:12.000+0200},
    title = {Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations},
    url = {https://www.aclweb.org/anthology/2021.wassa-1.17},
    year = 2021
    }

  • M. Overbeck, Die Rückkehr der Religion in die politische Öffentlichkeit: Eine korpusanalytische Untersuchung religiöser Frames in westlichen Mediendebatten über bewaffnete Konflikte nach dem Ende des Kalten Krieges (1990-2012), Tectum Verlag, 2021.
    [BibTeX] [Abstract] [Download PDF]

    Die Politisierung von Religion in bewaffneten Konflikten ist eine globale Herausforderung, die innerhalb politikwissenschaftlicher Debatten intensiv erforscht wird. Doch warum fällt es westlichen Gesellschaften so schwer, in kritische und differenzierte Formen der Auseinandersetzung mit religiösen Rechtfertigungen von Gewalt zu treten? Die empirischen Befunde zeigen erstmals auf Grundlage einer korpusanalytischen Langzeitanalyse westlicher Konfliktdebatten (460.917 Zeitungsartikel), wie religiöse Identitäten nach dem Ende des Kalten Krieges zu primären Referenzkategorien für die Beschreibung nicht-westlicher Kollektive werden. In diesem diskursiven Gesamtkontext entfalten religiöse Begründungen von Gewalt ihre besondere Wirkung.

    @book{overbeck2021rckkehr,
    abstract = {Die Politisierung von Religion in bewaffneten Konflikten ist eine globale Herausforderung, die innerhalb politikwissenschaftlicher Debatten intensiv erforscht wird. Doch warum fällt es westlichen Gesellschaften so schwer, in kritische und differenzierte Formen der Auseinandersetzung mit religiösen Rechtfertigungen von Gewalt zu treten? Die empirischen Befunde zeigen erstmals auf Grundlage einer korpusanalytischen Langzeitanalyse westlicher Konfliktdebatten (460.917 Zeitungsartikel), wie religiöse Identitäten nach dem Ende des Kalten Krieges zu primären Referenzkategorien für die Beschreibung nicht-westlicher Kollektive werden. In diesem diskursiven Gesamtkontext entfalten religiöse Begründungen von Gewalt ihre besondere Wirkung.},
    added-at = {2021-09-29T15:24:55.000+0200},
    author = {Overbeck, Max},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c3ceae23d3d076a0143228691334b556/sowi3},
    interhash = {98b66f46e8373a795a600e08a740e886},
    intrahash = {c3ceae23d3d076a0143228691334b556},
    isbn = {978-3-8288-4673-9},
    keywords = {eidentity sowi3},
    publisher = {Tectum Verlag},
    timestamp = {2021-10-08T14:23:47.000+0200},
    title = {Die Rückkehr der Religion in die politische Öffentlichkeit: Eine korpusanalytische Untersuchung religiöser Frames in westlichen Mediendebatten über bewaffnete Konflikte nach dem Ende des Kalten Krieges (1990-2012)},
    url = {https://www.nomos-shop.de/tectum/titel/die-rueckkehr-der-religion-in-die-politische-oeffentlichkeit-id-100432/},
    year = 2021
    }

  • E. Troiano, S. Padó, and R. Klinger, “Emotion Ratings: How Intensity, Annotation Confidence and Agreements are Entangled,” in Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 2021.
    [BibTeX] [Download PDF]
    @inproceedings{Troiano2021,
    added-at = {2021-03-04T19:47:08.000+0100},
    author = {Troiano, Enrica and Pad\'o, Sebastian and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/252358b0b6662fae9e48249176dde92c4/dr.romanklinger},
    booktitle = {Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {a45e19f1c5dcf24d27ac15de69a99b01},
    intrahash = {52358b0b6662fae9e48249176dde92c4},
    keywords = {nlp imported myown emotion},
    pdf = {http://www.romanklinger.de/publications/TroianoPadoKlingerWASSA2021.pdf},
    timestamp = {2021-04-26T15:28:26.000+0200},
    title = {Emotion Ratings: How Intensity, Annotation Confidence and Agreements are Entangled},
    url = {https://www.aclweb.org/anthology/2021.wassa-1.5/},
    year = 2021
    }

2020

  • A. Ahmad, K. Desta, F. Lang, and D. Schlechtweg, “Shared Task: Lexical Semantic Change Detection in German,” CoRR, vol. abs/2001.07786, 2020.
    [BibTeX] [Download PDF]
    @article{DBLP:journals/corr/abs-2001-07786,
    added-at = {2020-02-27T13:08:34.000+0100},
    archiveprefix = {arXiv},
    author = {Ahmad, Adnan and Desta, Kiflom and Lang, Fabian and Schlechtweg, Dominik},
    bibsource = {dblp computer science bibliography, https://dblp.org},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29001ae1c36092a316493812933adc0f4/dschlechtweg},
    eprint = {2001.07786},
    interhash = {feb40afc0d4e3fd674e1607bffae77ec},
    intrahash = {9001ae1c36092a316493812933adc0f4},
    journal = {CoRR},
    keywords = {myown},
    timestamp = {2020-03-15T01:38:56.000+0100},
    title = {Shared Task: Lexical Semantic Change Detection in German},
    url = {https://arxiv.org/abs/2001.07786},
    volume = {abs/2001.07786},
    year = 2020
    }

  • R. Alatrash, D. Schlechtweg, J. Kuhn, and S. Schulte im Walde, “CCOHA: Clean Corpus of Historical American English,” in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille, France, 2020, p. 6958–6966.
    [BibTeX] [Abstract] [Download PDF]

    Modelling language change is an increasingly important area of interest within the fields of sociolinguistics and historical linguistics. In recent years, there has been a growing number of publications whose main concern is studying changes that have occurred within the past centuries. The Corpus of Historical American English (COHA) is one of the most commonly used large corpora in diachronic studies in English. This paper describes methods applied to the downloadable version of the COHA corpus in order to overcome its main limitations, such as inconsistent lemmas and malformed tokens, without compromising its qualitative and distributional properties. The resulting corpus CCOHA contains a larger number of cleaned word tokens which can offer better insights into language change and allow for a larger variety of tasks to be performed.

    @inproceedings{alatrash-etal-2020-ccoha,
    abstract = {Modelling language change is an increasingly important area of interest within the fields of sociolinguistics and historical linguistics. In recent years, there has been a growing number of publications whose main concern is studying changes that have occurred within the past centuries. The Corpus of Historical American English (COHA) is one of the most commonly used large corpora in diachronic studies in English. This paper describes methods applied to the downloadable version of the COHA corpus in order to overcome its main limitations, such as inconsistent lemmas and malformed tokens, without compromising its qualitative and distributional properties. The resulting corpus CCOHA contains a larger number of cleaned word tokens which can offer better insights into language change and allow for a larger variety of tasks to be performed.},
    added-at = {2020-09-15T10:37:41.000+0200},
    address = {Marseille, France},
    author = {Alatrash, Reem and Schlechtweg, Dominik and Kuhn, Jonas and Schulte im Walde, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23a733b2d1c890bcf15c95b10c8149d56/dschlechtweg},
    booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference},
    interhash = {102667e878a6dc05a46a088652e08d9c},
    intrahash = {3a733b2d1c890bcf15c95b10c8149d56},
    isbn = {979-10-95546-34-4},
    keywords = {myown},
    language = {English},
    month = {05},
    pages = {6958--6966},
    publisher = {European Language Resources Association},
    timestamp = {2020-09-15T10:39:21.000+0200},
    title = {{CCOHA}: Clean Corpus of Historical {A}merican {E}nglish},
    url = {https://www.aclweb.org/anthology/2020.lrec-1.859},
    year = 2020
    }

  • M. Baumann, S. Koch, M. John, and T. Ertl, “Interactive Visualization for Reflected Text Analytics,” in Reflektierte Algorithmische Textanalyse, N. Reiter, A. Pichler, and J. Kuhn, Eds., Berlin: de Gruyter, 2020, p. 269–296. doi:10.1515/9783110693973-012
    [BibTeX]
    @incollection{Baumann.2020c,
    added-at = {2020-10-01T23:22:03.000+0200},
    address = {Berlin},
    author = {Baumann, Martin and Koch, Steffen and John, Markus and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/231c3db9c2c9b03d9b00dcf3d0eff233d/martinbaumann},
    booktitle = {{Reflektierte Algorithmische Textanalyse}},
    doi = {10.1515/9783110693973-012},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {18cb57443b8f8cdaca8f53ae4dffe7a0},
    intrahash = {31c3db9c2c9b03d9b00dcf3d0eff233d},
    isbn = {9783110693973},
    keywords = {vis-gis vis(us) visus:kochsn visus:ertl visus:baumanmn visus:johnms},
    pages = {269--296},
    publisher = {{de Gruyter}},
    timestamp = {2020-10-01T23:24:07.000+0200},
    title = {{Interactive Visualization for Reflected Text Analytics}},
    year = 2020
    }

  • M. Baumann, H. Minasyan, S. Koch, K. Kurzhals, and T. Ertl, “AnnoXplorer: A Scalable, Integrated Approach for the Visual Analysis of Text Annotations,” in Proc. 15th Int. Jt. Conf. Comput. Vis., Imaging and Comput. Graph. Theory and App. – IVAPP, 2020, p. 62–75.
    [BibTeX]
    @inproceedings{Baumann.2020,
    added-at = {2020-03-26T23:20:21.000+0100},
    author = {Baumann, Martin and Minasyan, Harutyun and Koch, Steffen and Kurzhals, Kuno and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/250315f5caccf62dfed50f69707ab8991/martinbaumann},
    booktitle = {Proc. 15th Int. Jt. Conf. Comput. Vis., Imaging and Comput. Graph. Theory and App. - IVAPP},
    interhash = {1c54da365316d679c7180ef4b59455bd},
    intrahash = {50315f5caccf62dfed50f69707ab8991},
    keywords = {myown vis-gis vis(us) visus:kochsn visus:ertl visus:kurzhako visus:baumanmn visus:johnms},
    pages = {62--75},
    timestamp = {2020-03-27T10:49:50.000+0100},
    title = {{AnnoXplorer: A Scalable, Integrated Approach for the Visual Analysis of Text Annotations}},
    year = 2020
    }

  • A. Blessing, M. John, S. Koch, E. Thomas, and K. Jonas, “Reflected Text Analytics through Interactive Visualization,” in LingVis: Visual Analytics for Linguistics, B. Miriam, H. Annette, and L. Verena, Eds., Stanford: CSLI Publications, 2020.
    [BibTeX] [Download PDF]
    @incollection{blessing2020reflected,
    added-at = {2021-06-05T10:18:29.000+0200},
    address = {Stanford},
    author = {Blessing, Andre and John, Markus and Koch, Steffen and Thomas, Ertl and Jonas, Kuhn},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26edd3bf20e41b077558cca155b77a280/blessing},
    booktitle = {LingVis: Visual Analytics for Linguistics},
    editor = {Miriam, Butt and Annette, Hautli-Janisz and Verena, Lyding},
    interhash = {cb2fcf1d3c0080d6b19723fc9a425313},
    intrahash = {6edd3bf20e41b077558cca155b77a280},
    isbn = {1684000351},
    keywords = {creta},
    publisher = {CSLI Publications},
    series = {Lecture Notes},
    timestamp = {2021-06-05T10:39:42.000+0200},
    title = {Reflected Text Analytics through Interactive Visualization},
    url = {https://web.stanford.edu/group/cslipublications/cslipublications/site/9781684000333.shtml},
    year = 2020
    }

  • N. Blokker, E. Dayanik, G. Lapesa, and S. Padó, “Swimming with the Tide? Positional Claim Detection across Political Text Types,” in Proceedings of the NLP+CSS workshop, Online, 2020, p. 24–34.
    [BibTeX] [Download PDF]
    @inproceedings{blokker20:_swimm_tide,
    added-at = {2020-10-02T09:43:59.000+0200},
    address = {Online},
    author = {Blokker, Nico and Dayanik, Erenay and Lapesa, Gabriella and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c8caad10654ddbc031a19634a4204f7a/sp},
    booktitle = {Proceedings of the {NLP+CSS} workshop},
    interhash = {9399eb41d74c6c2be84a191bfa6d1885},
    intrahash = {c8caad10654ddbc031a19634a4204f7a},
    keywords = {myown workshop},
    pages = {24--34},
    timestamp = {2020-11-11T21:06:25.000+0100},
    title = {Swimming with the Tide? Positional Claim Detection across Political Text Types},
    url = {https://www.aclweb.org/anthology/2020.nlpcss-1.3/},
    year = 2020
    }

  • L. A. M. Bostan, E. Kim, and R. Klinger, “GoodNewsEveryone: A Corpus of News Headlines Annotated with Emotions, Semantic Roles, and Reader Perception,” in Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC’20), Marseille, France, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{Bostan2020,
    added-at = {2020-05-14T11:08:28.000+0200},
    address = {Marseille, France},
    author = {Bostan, Laura Ana Maria and Kim, Evgeny and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/219d29420f39eed98de00d8354eaa9fdb/dr.romanklinger},
    booktitle = {Proceedings of the 12th International Conference on Language Resources  and Evaluation (LREC'20)},
    editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
    interhash = {09dc94a77b066ae65fc08f2930c6d6a1},
    intrahash = {19d29420f39eed98de00d8354eaa9fdb},
    keywords = {nlp imported myown emotion},
    language = {english},
    month = {05},
    pdf = {http://www.romanklinger.de/publications/BostanKimKlinger2020LREC.pdf},
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2020-08-03T12:38:46.000+0200},
    title = {{GoodNewsEveryone}: A Corpus of News Headlines Annotated with Emotions, Semantic Roles, and Reader Perception},
    url = {https://www.aclweb.org/anthology/2020.lrec-1.194},
    year = 2020
    }

  • E. Dayanik and S. Padó, “Masking Actor Information Leads to Fairer Political Claims Detection,” in Proceedings of ACL, Online, 2020, pp. 4385-4391.
    [BibTeX] [Abstract] [Download PDF]

    A central concern in Computational Social Sciences (CSS) is fairness: where the role of NLP is to scale up text analysis to large corpora, the quality of automatic analyses should be as independent as possible of textual properties. We analyze the performance of a state-of-the-art neural model on the task of political claims detection (i.e., the identification of forward-looking statements made by political actors) and identify a strong frequency bias: claims made by frequent actors are recognized better. We propose two simple debiasing methods which mask proper names and pronouns during training of the model, thus removing personal information bias. We find that (a) these methods significantly decrease frequency bias while keeping the overall performance stable; and (b) the resulting models improve when evaluated in an out-of-domain setting.

    @inproceedings{dayanik20:_maskin_actor_infor_leads_fairer,
    abstract = {A central concern in Computational Social Sciences (CSS) is fairness: where the role of NLP is to scale up text analysis to large corpora, the quality of automatic analyses should be as independent as possible of textual properties. We analyze the performance of a state-of-the-art neural model on the task of political claims detection (i.e., the identification of forward-looking statements made by political actors) and identify a strong frequency bias: claims made by frequent actors are recognized better. We propose two simple debiasing methods which mask proper names and pronouns during training of the model, thus removing personal information bias. We find that (a) these methods significantly decrease frequency bias while keeping the overall performance stable; and (b) the resulting models improve when evaluated in an out-of-domain setting.},
    added-at = {2020-04-04T15:05:44.000+0200},
    address = {Online},
    author = {Dayanik, Erenay and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23293989e68e3eda1db5018a5ac18dee4/sp},
    booktitle = {Proceedings of ACL},
    interhash = {00061c6a1cf89353a1c20cb29b483974},
    intrahash = {3293989e68e3eda1db5018a5ac18dee4},
    keywords = {myown conference},
    pages = {4385-4391},
    timestamp = {2020-12-07T16:42:14.000+0100},
    title = {Masking Actor Information Leads to Fairer Political Claims Detection},
    url = {https://www.aclweb.org/anthology/2020.acl-main.404/},
    year = 2020
    }

  • T. Haider, S. Eger, E. Kim, R. Klinger, and W. Menninghaus, “PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry,” in Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC’20), Marseille, France, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{Haider2020,
    added-at = {2020-05-14T11:08:28.000+0200},
    address = {Marseille, France},
    author = {Haider, Thomas and Eger, Steffen and Kim, Evgeny and Klinger, Roman and Menninghaus, Winfried},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2edaca295bc7c341649c293088cd04a5f/dr.romanklinger},
    booktitle = {Proceedings of the 12th International Conference on Language Resources  and Evaluation (LREC'20)},
    editor = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
    interhash = {f5205729ab22101b172e790f1ec48f98},
    intrahash = {edaca295bc7c341649c293088cd04a5f},
    keywords = {nlp imported myown emotion},
    language = {english},
    month = {05},
    pdf = {http://www.romanklinger.de/publications/HaiderEgerKimKlingerMenninghaus2020LREC_PO-EMO.pdf},
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2020-08-03T12:38:24.000+0200},
    title = {{PO-EMO}: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in {German} and {English} Poetry},
    url = {https://www.aclweb.org/anthology/2020.lrec-1.205},
    year = 2020
    }

  • S. Haunss, J. Kuhn, S. Pado, A. Blessing, N. Blokker, E. Dayanik, and G. Lapesa, “Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets,” Politics and Governance, vol. 8, iss. 2, 2020.
    [BibTeX] [Abstract] [Download PDF]

    This article investigates the integration of machine learning in the political claim annotation workflow with the goal to partially automate the annotation and analysis of large text corpora. It introduces the MARDY annotation environment and presents results from an experiment in which the annotation quality of annotators with and without machine learning based annotation support is compared. The design and setting aim to measure and evaluate: a) annotation speed; b) annotation quality; and c) applicability to the use case of discourse network generation. While the results indicate only slight increases in terms of annotation speed, the authors find a moderate boost in annotation quality. Additionally, with the help of manual annotation of the actors and filtering out of the false positives, the machine learning based annotation suggestions allow the authors to fully recover the core network of the discourse as extracted from the articles annotated during the experiment. This is due to the redundancy which is naturally present in the annotated texts. Thus, assuming a research focus not on the complete network but the network core, an AI-based annotation can provide reliable information about discourse networks with much less human intervention than compared to the traditional manual approach.

    @article{haunss20:_integ_manual_autom_annot_creat,
    abstract = {This article investigates the integration of machine learning in the political claim annotation workflow with the goal to partially automate the annotation and analysis of large text corpora. It introduces the MARDY annotation environment and presents results from an experiment in which the annotation quality of annotators with and without machine learning based annotation support is compared. The design and setting aim to measure and evaluate: a) annotation speed; b) annotation quality; and c) applicability to the use case of discourse network generation. While the results indicate only slight increases in terms of annotation speed, the authors find a moderate boost in annotation quality. Additionally, with the help of manual annotation of the actors and filtering out of the false positives, the machine learning based annotation suggestions allow the authors to fully recover the core network of the discourse as extracted from the articles annotated during the experiment. This is due to the redundancy which is naturally present in the annotated texts. Thus, assuming a research focus not on the complete network but the network core, an AI-based annotation can provide reliable information about discourse networks with much less human intervention than compared to the traditional manual approach.},
    added-at = {2020-03-23T20:19:19.000+0100},
    author = {Haunss, Sebastian and Kuhn, Jonas and Pado, Sebastian and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Lapesa, Gabriella},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24dcbda0eb92af231eef2b033d8d51b23/sp},
    interhash = {31dfa8365630383946e268e14bca9968},
    intrahash = {4dcbda0eb92af231eef2b033d8d51b23},
    journal = {Politics and Governance},
    keywords = {myown article},
    number = 2,
    timestamp = {2020-06-02T16:24:19.000+0200},
    title = {Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets},
    url = {http://dx.doi.org/10.17645/pag.v8i2.2591},
    volume = 8,
    year = 2020
    }

  • D. Helbig, E. Troiano, and R. Klinger, “Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline,” in Proceedings of the International Workshop on Natural Language Processing for Social Media (SocialNLP), Seattle, USA/Online, 2020. doi:10.18653/v1/2020.socialnlp-1.6
    [BibTeX] [Download PDF]
    @inproceedings{Helbig2020,
    added-at = {2020-05-14T11:08:28.000+0200},
    address = {Seattle, USA/Online},
    author = {Helbig, David and Troiano, Enrica and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23c1c2b56ae52fd3c545d811f5912ddc8/dr.romanklinger},
    booktitle = {Proceedings of the International Workshop on Natural Language Processing for Social Media (SocialNLP)},
    doi = {10.18653/v1/2020.socialnlp-1.6},
    interhash = {b075f930cd519af57cb4d56ee3099843},
    intrahash = {3c1c2b56ae52fd3c545d811f5912ddc8},
    keywords = {nlp imported myown emotion},
    organization = {Association for Computational Linguistics},
    timestamp = {2020-08-03T12:38:02.000+0200},
    title = {Challenges in Emotion Style Transfer: An Exploration with a
    Lexical Substitution Pipeline},
    url = {https://www.aclweb.org/anthology/2020.socialnlp-1.6},
    year = 2020
    }

  • A. Hätty, D. Schlechtweg, M. Dorna, and S. Schulte im Walde, “Predicting Degrees of Technicality in Automatic Terminology Extraction,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 2020, p. 2883–2889. doi:10.18653/v1/2020.acl-main.258
    [BibTeX] [Abstract] [Download PDF]

    While automatic term extraction is a well-researched area, computational approaches to distinguish between degrees of technicality are still understudied. We semi-automatically create a German gold standard of technicality across four domains, and illustrate the impact of a web-crawled general-language corpus on technicality prediction. When defining a classification approach that combines general-language and domain-specific word embeddings, we go beyond previous work and align vector spaces to gain comparative embeddings. We suggest two novel models to exploit general- vs. domain-specific comparisons: a simple neural network model with pre-computed comparative-embedding information as input, and a multi-channel model computing the comparison internally. Both models outperform previous approaches, with the multi-channel model performing best.

    @inproceedings{hatty-etal-2020-predicting,
    abstract = {While automatic term extraction is a well-researched area, computational approaches to distinguish between degrees of technicality are still understudied. We semi-automatically create a German gold standard of technicality across four domains, and illustrate the impact of a web-crawled general-language corpus on technicality prediction. When defining a classification approach that combines general-language and domain-specific word embeddings, we go beyond previous work and align vector spaces to gain comparative embeddings. We suggest two novel models to exploit general- vs. domain-specific comparisons: a simple neural network model with pre-computed comparative-embedding information as input, and a multi-channel model computing the comparison internally. Both models outperform previous approaches, with the multi-channel model performing best.},
    added-at = {2020-09-15T10:40:40.000+0200},
    address = {Online},
    author = {H{\"a}tty, Anna and Schlechtweg, Dominik and Dorna, Michael and Schulte im Walde, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a91ca0b6505dc88d4c7670dc99e4a546/dschlechtweg},
    booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
    doi = {10.18653/v1/2020.acl-main.258},
    interhash = {d1fee1795e6d73c2aaacfda937f80568},
    intrahash = {a91ca0b6505dc88d4c7670dc99e4a546},
    keywords = {myown},
    month = {07},
    pages = {2883--2889},
    publisher = {Association for Computational Linguistics},
    timestamp = {2020-09-15T10:40:40.000+0200},
    title = {Predicting Degrees of Technicality in Automatic Terminology Extraction},
    url = {https://www.aclweb.org/anthology/2020.acl-main.258},
    year = 2020
    }

  • J. Kaiser, D. Schlechtweg, and S. {Schulte im Walde}, “OP-IMS @ DIACR-Ita: Back to the Roots: SGNS+OP+CD still rocks Semantic Change Detection,” in Proceedings of the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2020), Online, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{kaiser-etal-2020-roots,
    added-at = {2020-11-13T02:25:04.000+0100},
    address = {Online},
    author = {Kaiser, Jens and Schlechtweg, Dominik and {Schulte im Walde}, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2121928d4b68d4d22e844b5314d137336/dschlechtweg},
    booktitle = {{Proceedings of the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2020)}},
    editor = {Basile, Valerio and Croce, Danilo and Di Maro, Maria and Passaro, Lucia C.},
    interhash = {0eda20462cafdfa0344c6d9b4f3995cf},
    intrahash = {121928d4b68d4d22e844b5314d137336},
    keywords = {myown},
    publisher = {CEUR.org},
    timestamp = {2020-11-13T02:25:04.000+0100},
    title = {{OP-IMS @ DIACR-Ita: Back to the Roots: SGNS+OP+CD still rocks Semantic Change Detection}},
    url = {https://arxiv.org/abs/2011.03258},
    year = 2020
    }

  • J. Kaiser, D. Schlechtweg, S. Papay, and S. Schulte {im Walde}, “IMS at SemEval-2020 Task 1: How low can you go? Dimensionality in Lexical Semantic Change Detection,” in Proceedings of the 14th International Workshop on Semantic Evaluation, Barcelona, Spain, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{kaiser-etal-2020-IMS,
    added-at = {2020-09-15T10:45:44.000+0200},
    address = {Barcelona, Spain},
    author = {Kaiser, Jens and Schlechtweg, Dominik and Papay, Sean and Schulte {im Walde}, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/287d0340610ebadd7e6ffce066b5b35a8/dschlechtweg},
    booktitle = {Proceedings of the 14th International Workshop on Semantic Evaluation},
    interhash = {8a21f295fd01c31fd7f46ccb418efb28},
    intrahash = {87d0340610ebadd7e6ffce066b5b35a8},
    keywords = {myown},
    publisher = {Association for Computational Linguistics},
    timestamp = {2020-09-15T10:49:45.000+0200},
    title = {{IMS} at {S}em{E}val-2020 {T}ask 1: {How low can you go? Dimensionality in Lexical Semantic Change Detection}},
    url = {https://arxiv.org/abs/2008.03164},
    year = 2020
    }

  • C. Kantner and M. Overbeck, “Exploring Soft Concepts with Hard Corpus-Analytic Methods,” in Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt, N. Reiter, A. Pichler, and J. Kuhn, Eds., Berlin: De Gruyter, 2020, pp. 128-141.
    [BibTeX]
    @inbook{kantner2020exploring,
    added-at = {2020-08-01T15:21:38.000+0200},
    address = {Berlin},
    author = {Kantner, Cathleen and Overbeck, Max},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2ea247732f44956e44b57945588ab6619/sowi3},
    booktitle = {Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {9e3e5584bf81fecbca663f9a8b63b888},
    intrahash = {ea247732f44956e44b57945588ab6619},
    keywords = {cathleenkantner creta eidentity sowi3},
    pages = {128-141},
    publisher = {De Gruyter},
    series = {Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    timestamp = {2021-09-11T16:56:05.000+0200},
    title = {Exploring Soft Concepts with Hard Corpus-Analytic Methods},
    year = 2020
    }

  • J. Keck, M. Knabben, and S. Padó, Who’s in the news? Methodological challenges and opportunities in studying 19th century writers in historical newspapers, 2020.
    [BibTeX]
    @misc{keck20:_whos,
    added-at = {2021-02-04T20:11:59.000+0100},
    author = {Keck, Jana and Knabben, Mortitz and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2273cbdcd12aee90780cae7cc608b508e/sp},
    howpublished = {\textit{Europeanatech Insight, Issue 16: Newspapers}},
    interhash = {72cba44c7148ad557beaeea0caa7a0fb},
    intrahash = {273cbdcd12aee90780cae7cc608b508e},
    keywords = {myown abstract},
    note = {\url{https://pro.europeana.eu/page/issue-16-newspapers#who-s-in-the-news}},
    timestamp = {2021-02-04T20:11:59.000+0100},
    title = {Who's in the news? Methodological challenges and opportunities in studying 19th century writers in historical newspapers},
    year = 2020
    }

  • N. Ketschik, B. Krautter, S. Murr, J. Pagel, and N. Reiter, “Vom Phänomen zur Analyse – ein CRETA-Workshop zur reflektierten Operationalisierung in den DH,” in Digital Humanities im deutschsprachigen Raum 2020., 2020, pp. 52-55.
    [BibTeX]
    @conference{noauthororeditor,
    added-at = {2020-03-23T21:00:23.000+0100},
    author = {Ketschik, Nora and Krautter, Benjamin and Murr, Sandra and Pagel, Janis and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2864406b2c120877abae947321fcea055/nora-ketschik},
    booktitle = {Digital Humanities im deutschsprachigen Raum 2020.},
    interhash = {bde9e7277242473304569b574ce855c4},
    intrahash = {864406b2c120877abae947321fcea055},
    keywords = {DH Operationalisierung},
    pages = {52-55},
    timestamp = {2020-03-23T21:00:23.000+0100},
    title = {Vom Phänomen zur Analyse - ein CRETA-Workshop zur reflektierten Operationalisierung in den DH},
    year = 2020
    }

  • N. Ketschik, Y. Zimmermann, S. Murr, and B. Krautter, “Zur Theorie von Erzählebenen und ihrer Annotation im digitalen Kontext,” in Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt, N. Reiter, A. Pichler, and J. Kuhn, Eds., , 2020, p. 439–464.
    [BibTeX]
    @incollection{ketschik2020theorie,
    added-at = {2020-10-16T11:20:18.000+0200},
    author = {Ketschik, Nora and Zimmermann, Yvonne and Murr, Sandra and Krautter, Benjamin},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25b387d50f609838f5e5302f2f0d76d2e/noraketschik},
    booktitle = {Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {61f2c107532f807c1c67f6696748837b},
    intrahash = {5b387d50f609838f5e5302f2f0d76d2e},
    keywords = {annotation myown dh narratology},
    pages = {439–464},
    timestamp = {2020-10-19T10:42:31.000+0200},
    title = {Zur Theorie von Erzählebenen und ihrer Annotation im digitalen Kontext},
    year = 2020
    }

  • N. Ketschik, M. Overbeck, S. Murr, A. Pichler, and A. Blessing, “Interdisziplinäre Annotation von Entitätenreferenzen,” in Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt, N. Reiter, A. Pichler, and J. Kuhn, Eds., , 2020, pp. 203-263.
    [BibTeX]
    @inbook{ketschik2020interdisziplinre,
    added-at = {2020-10-16T11:10:12.000+0200},
    author = {Ketschik, Nora and Overbeck, Maximilian and Murr, Sandra and Pichler, Axel and Blessing, André},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/273afc7ba8b433153e5a2a2be6f1ed5b1/noraketschik},
    booktitle = {Reflektierte algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {99ba41f67f88e6a4abea1f718d2adf0c},
    intrahash = {73afc7ba8b433153e5a2a2be6f1ed5b1},
    keywords = {annotation myown DH},
    pages = {203-263},
    timestamp = {2020-10-19T10:42:44.000+0200},
    title = {Interdisziplinäre Annotation von Entitätenreferenzen},
    year = 2020
    }

  • G. Khalilpour, Western Conceptions of Democracy and the Transatlantic Divide over Democracy Promotion. Media Debates in the Context of Military Intervention, Baden-Baden: Nomos, 2020.
    [BibTeX] [Download PDF]
    @book{khalilpour2020western,
    added-at = {2020-04-29T10:21:52.000+0200},
    address = {Baden-Baden},
    author = {Khalilpour, Golareh},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2812c825b47f6f413738216ebaf52352b/sowi3},
    interhash = {43651cb2a8ffda21835b83b46b107e83},
    intrahash = {812c825b47f6f413738216ebaf52352b},
    keywords = {eidentity GolarehKhalilpour sowi3},
    publisher = {Nomos},
    timestamp = {2020-08-01T15:15:17.000+0200},
    title = {Western Conceptions of Democracy and the Transatlantic Divide over Democracy Promotion. Media Debates in the Context of Military Intervention },
    url = {https://www.nomos-shop.de/titel/western-conceptions-of-democracy-and-the-transatlantic-divide-over-democracy-promotion-id-74828/},
    year = 2020
    }

  • R. Klinger, “Strukturierte Modellierung von Affekt in Text,” habilitation PhD Thesis, Stuttgart, Germany, 2020.
    [BibTeX] [Download PDF]
    @phdthesis{klinger2020strukturierte,
    added-at = {2020-08-03T12:40:56.000+0200},
    address = {Stuttgart, Germany},
    author = {Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/296d5a4633df438c8b4d6cab2951a69af/dr.romanklinger},
    interhash = {5f8c3a9a1927308994af9eb53c935cf0},
    intrahash = {96d5a4633df438c8b4d6cab2951a69af},
    keywords = {sentiment nlp myown emotion affect},
    language = {english},
    school = {University of Stuttgart},
    timestamp = {2020-08-03T12:40:56.000+0200},
    title = {Strukturierte Modellierung von Affekt in Text},
    type = {habilitation},
    url = {http://romanklinger.de/publications/habilitation/Klinger-Affekt-in-Text-Habil-2020.pdf},
    year = 2020
    }

  • R. Klinger, E. Kim, and S. Padó, “Emotion Analysis for Literary Studies,” in Reflected Computational Text Analysis, N. Reiter, A. Pichler, and J. Kuhn, Eds., De Gruyter, 2020, p. 237–268.
    [BibTeX] [Abstract] [Download PDF]

    Most approaches to emotion analysis in fictional texts focus on detecting the emotion class expressed over the course of a text, either with machine learning-based classification or with dictionaries. These approaches do not consider who experiences the emotion and what triggers it and therefore, as a necessary simplicifaction, aggregate across different characters and events. This constitutes a research gap, as emotions play a crucial role in the interaction between characters and the events they are involved in. We fill this gap with the development of two corpora and associated computational models which represent individual events together with their experiencers and stimuli. The first resource, REMAN (Relational EMotion ANnotation), aims at a fine-grained annotation of all these aspects on the text level. The second corpus, FANFIC, contains complete stories, annotated on the experiencer-stimulus level, i. e., focuses on emotional relations among characters. FANFIC is therefore a character relation corpus while REMAN considers event descriptions in addition. Our experiments show that computational stimuli detection is particularly challenging. Furthermore, predicting roles in joint models has the potential to perform better than separate predictions. These resources provide a starting point for future research on the recognition of emotions and associated entities in text. They support qualitative literary studies and digital humanities research. The corpora are freely available at http://www.ims.uni-stuttgart.de/data/emotion.

    @incollection{klinger20:_emotion_analy_liter_studies,
    abstract = {Most approaches to emotion analysis in fictional texts focus on detecting the emotion class expressed over the course of a text, either with machine learning-based classification or with dictionaries. These approaches do not consider who experiences the emotion and what triggers it and therefore, as a necessary simplicifaction, aggregate across different characters and events. This constitutes a research gap, as emotions play a crucial role in the interaction between characters and the events they are involved in. We fill this gap with the development of two corpora and associated computational models which represent individual events together with their experiencers and stimuli. The first resource, REMAN (Relational EMotion ANnotation), aims at a fine-grained annotation of all these aspects on the text level. The second corpus, FANFIC, contains complete stories, annotated on the experiencer-stimulus level, i. e., focuses on emotional relations among characters. FANFIC is therefore a character relation corpus while REMAN considers event descriptions in addition. Our experiments show that computational stimuli detection is particularly challenging. Furthermore, predicting roles in joint models has the potential to perform better than separate predictions. These resources provide a starting point for future research on the recognition of emotions and associated entities in text. They support qualitative literary studies and digital humanities research. The corpora are freely available at http://www.ims.uni-stuttgart.de/data/emotion.},
    added-at = {2020-07-29T09:52:40.000+0200},
    author = {Klinger, Roman and Kim, Evgeny and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23f005472d252b1b6648b2903c2dda625/sp},
    booktitle = {Reflected Computational Text Analysis},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {0a17b8df3b26cb2fed025c4ef3168cdd},
    intrahash = {3f005472d252b1b6648b2903c2dda625},
    keywords = {myown},
    pages = {237--268},
    publisher = {De Gruyter},
    timestamp = {2020-07-29T09:55:37.000+0200},
    title = {Emotion Analysis for Literary Studies},
    url = {https://doi.org/10.1515/9783110693973-011},
    year = 2020
    }

  • R. Klinger, E. Kim, and S. Padó, “Emotion Analysis for Literary Studies,” in Reflektierte Algorithmische Textanalyse, N. Reiter, A. Pichler, and J. Kuhn, Eds., Berlin/Boston: De Gruyter, 2020.
    [BibTeX]
    @incollection{Klinger2020,
    added-at = {2020-05-14T11:08:28.000+0200},
    address = {Berlin/Boston},
    author = {Klinger, Roman and Kim, Evgeny and Pad\'o, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/26be8276caaacd08542cb703592a0b26c/dr.romanklinger},
    booktitle = {Reflektierte Algorithmische Textanalyse},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {793d5c4d5e32983bbb571ef2beae6e7d},
    intrahash = {6be8276caaacd08542cb703592a0b26c},
    keywords = {nlp imported myown emotion},
    note = {to appear},
    publisher = {De Gruyter},
    timestamp = {2020-05-14T11:09:47.000+0200},
    title = {Emotion Analysis for Literary Studies},
    year = 2020
    }

  • B. Krautter, J. Pagel, N. Reiter, and M. Willand, “„[E]in Vater, dächte ich, ist doch immer ein Vater“. Figurentypen und ihre Operationalisierung,” Zeitschrift für digitale Geisteswissenschaften, vol. 5, iss. 7, 2020. doi:10.17175/2020_007
    [BibTeX] [Abstract] [Download PDF]

    Dieser Artikel behandelt die Operationalisierung von Figurentypen im deutschsprachigen Drama. Ausgehend von der dramen- und theatergeschichtlichen Forschung werden Figuren bestimmt, die einem der drei Figurentypen ›Intrigant*in‹, ›tugendhafte Tochter‹ und ›zärtlicher Vater‹ entsprechen. Für die Figuren wurden eigenschaftsbasierte Datensätze erstellt, die zu ihrer automatischen Klassifikation herangezogen werden. Neben die inhaltliche Komplexität von Figuren und die theoretische Bestimmung von Figurentypen tritt die methodische Herausforderung, ausgehend von einer kleinen Menge an Annotationen zu generalisieren. Unsere Experimente zeigen, dass sich die gewählten Typen jeweils innerhalb einer Grundgesamtheit als abgrenzbare Teilmengen herausbilden.

    @article{krautter2020a,
    abstract = {Dieser Artikel behandelt die Operationalisierung von Figurentypen im deutschsprachigen Drama. Ausgehend von der dramen- und theatergeschichtlichen Forschung werden Figuren bestimmt, die einem der drei Figurentypen ›Intrigant*in‹, ›tugendhafte Tochter‹ und ›zärtlicher Vater‹ entsprechen. Für die Figuren wurden eigenschaftsbasierte Datensätze erstellt, die zu ihrer automatischen Klassifikation herangezogen werden. Neben die inhaltliche Komplexität von Figuren und die theoretische Bestimmung von Figurentypen tritt die methodische Herausforderung, ausgehend von einer kleinen Menge an Annotationen zu generalisieren. Unsere Experimente zeigen, dass sich die gewählten Typen jeweils innerhalb einer Grundgesamtheit als abgrenzbare Teilmengen herausbilden.},
    added-at = {2021-06-22T13:29:41.000+0200},
    author = {Krautter, Benjamin and Pagel, Janis and Reiter, Nils and Willand, Marcus},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/242e37838377e91751a223bebfdf5c00c/janispagel},
    doi = {10.17175/2020_007},
    interhash = {ec41d8af7772d2a5336b111b04a294fb},
    intrahash = {42e37838377e91751a223bebfdf5c00c},
    journal = {Zeitschrift für digitale Geisteswissenschaften},
    keywords = {annotation myown cls classification},
    language = {German},
    month = {12},
    number = 7,
    timestamp = {2021-06-22T13:30:25.000+0200},
    title = {„[E]in Vater, dächte ich, ist doch immer ein Vater“. Figurentypen und ihre Operationalisierung},
    url = {http://www.zfdg.de/2020_007},
    volume = 5,
    year = 2020
    }

  • G. Kremer and K. Jung, “Maschinelles Lernen lernen: Ein CRETA-Hackatorial zur reflektierten automatischen Textanalyse,” in DHd 2020 Digital Spielräume: Digital Humanities zwischen Modellierung und Interpretation. Conference abstracts, Paderborn, Germany, 2020, p. 33–36.
    [BibTeX] [Download PDF]
    @inproceedings{KremerJungDHd20:MaschLern,
    added-at = {2020-03-09T13:01:38.000+0100},
    address = {Paderborn, Germany},
    author = {Kremer, Gerhard and Jung, Kerstin},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d7e8586d43efa51e6849c243f8628a61/drgerhardkremer},
    booktitle = {DHd 2020 Digital Spielr{\"a}ume: Digital Humanities zwischen Modellierung und Interpretation. Conference abstracts},
    interhash = {ff475e2e164a13e65767f5a7e8652fbf},
    intrahash = {d7e8586d43efa51e6849c243f8628a61},
    keywords = {myown workshop creta},
    month = {02},
    pages = {33--36},
    publisher = {Christof Schöch},
    timestamp = {2020-03-09T13:01:38.000+0100},
    title = {Maschinelles {L}ernen lernen: {E}in
    {CRETA}-{H}ackatorial zur reflektierten
    automatischen {T}extanalyse},
    url = {https://doi.org/10.5281/zenodo.3666690},
    year = 2020
    }

  • S. Laicher, G. Baldissin, E. Castaneda, D. Schlechtweg, and S. {Schulte im Walde}, “CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection,” in Proceedings of the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2020), Online, 2020.
    [BibTeX]
    @inproceedings{laicher-etal-2020-volente,
    added-at = {2020-11-13T02:18:21.000+0100},
    address = {Online},
    author = {Laicher, Severin and Baldissin, Gioia and Castaneda, Enrique and Schlechtweg, Dominik and {Schulte im Walde}, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2fcc2b2cbb5daed05b54692bb6ed9f1bd/dschlechtweg},
    booktitle = {{Proceedings of the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2020)}},
    editor = {Basile, Valerio and Croce, Danilo and Di Maro, Maria and Passaro, Lucia C.},
    interhash = {28b88e1457314c1259a0e3b0fbd548b9},
    intrahash = {fcc2b2cbb5daed05b54692bb6ed9f1bd},
    keywords = {myown},
    publisher = {CEUR.org},
    timestamp = {2020-11-13T02:19:47.000+0100},
    title = {{CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection}},
    year = 2020
    }

  • G. Lapesa, A. Blessing, N. Blokker, E. Dayanik, S. Haunss, J. Kuhn, and S. Padó, “Analysis of Political Debates through Newspaper Reports: Methods and Outcomes,” Datenbank-Spektrum, vol. 20, iss. 2, 2020.
    [BibTeX] [Abstract] [Download PDF]

    Discourse network analysis is an aspiring development in political science which analyzes political debates in terms of bipartite actor/claim networks. It aims at understanding the structure and temporal dynamics of major political debates as instances of politicized democratic decision making. We discuss how such networks can be constructed on the basis of large collections of unstructured text, namely newspaper reports. We sketch a hybrid methodology of manual analysis by domain experts complemented by machine learning and exemplify it on the case study of the German public debate on immigration in the year 2015. The first half of our article sketches the conceptual building blocks of discourse network analysis and demonstrates its application. The second half discusses the potential of the application of NLP methods to support the creation of discourse network datasets.

    @article{lapesa20:_analy_polit_debat_newsp_repor,
    abstract = {Discourse network analysis is an aspiring development in political science which analyzes political debates in terms of bipartite actor/claim networks. It aims at understanding the structure and temporal dynamics of major political debates as instances of politicized democratic decision making. We discuss how such networks can be constructed on the basis of large collections of unstructured text, namely newspaper reports. We sketch a hybrid methodology of manual analysis by domain experts complemented by machine learning and exemplify it on the case study of the German public debate on immigration in the year 2015. The first half of our article sketches the conceptual building blocks of discourse network analysis and demonstrates its application. The second half discusses the potential of the application of NLP methods to support the creation of discourse network datasets.},
    added-at = {2020-05-29T15:45:59.000+0200},
    author = {Lapesa, Gabriella and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24226ed780f206d3d17058c3482f81bf1/sp},
    interhash = {cfd5940a96a17ad172311fe643cff81b},
    intrahash = {4226ed780f206d3d17058c3482f81bf1},
    journal = {Datenbank-Spektrum},
    keywords = {myown article},
    number = 2,
    timestamp = {2020-06-18T16:40:56.000+0200},
    title = {Analysis of Political Debates through Newspaper Reports: Methods and Outcomes},
    url = {http://dx.doi.org/10.1007/s13222-020-00344-w},
    volume = 20,
    year = 2020
    }

  • G. Lapesa, A. Blessing, N. Blokker, E. Dayanik, S. Haunss, J. Kuhn, and S. Padó, “DEbateNet-mig15: Tracing the 2015 Immigration Debate in Germany Over Time,” in Proceedings of LREC, Online, 2020, p. 919–927.
    [BibTeX] [Abstract] [Download PDF]

    DEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate.

    @inproceedings{lapesa2020debatenetmig15,
    abstract = {DEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate.},
    added-at = {2020-02-11T14:44:55.000+0100},
    address = {Online},
    author = {Lapesa, Gabriella and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23e4f84069e33ea38700b4b9e36f6e61e/sp},
    booktitle = {Proceedings of LREC},
    interhash = {351c134387fd9e594c83bc773b14529e},
    intrahash = {3e4f84069e33ea38700b4b9e36f6e61e},
    keywords = {myown conference},
    pages = {919--927},
    timestamp = {2020-12-07T16:42:49.000+0100},
    title = {{DEbateNet-mig15}: {T}racing the 2015 Immigration Debate in {G}ermany Over Time},
    url = {https://www.aclweb.org/anthology/2020.lrec-1.115},
    year = 2020
    }

  • I. Nothofer, Verblendete Öffentlichkeiten. Blinde Flecken in der Debatte über humanitäre militärische Interventionen, Weilerswist: Velbrück Wissenschaft, 2020.
    [BibTeX] [Download PDF]
    @book{nothofer2020verblendete,
    added-at = {2020-08-01T15:09:22.000+0200},
    address = {Weilerswist},
    author = {Nothofer, Iris},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a293207871c5c465398eeb1fcdb5efd7/sowi3},
    interhash = {cea6b4853bc0e3e415a56e722f8f0811},
    intrahash = {a293207871c5c465398eeb1fcdb5efd7},
    keywords = {creta eidentity sowi3 sowi3send:unibiblio},
    publisher = {Velbrück Wissenschaft},
    timestamp = {2021-09-29T15:13:03.000+0200},
    title = {Verblendete Öffentlichkeiten. Blinde Flecken in der Debatte über humanitäre militärische Interventionen},
    url = {https://www.velbrueck.de/Programm/Neuerscheinungen/Verblendete-Oeffentlichkeiten.html},
    year = 2020
    }

  • L. Oberländer, K. Reich, and R. Klinger, “Emotional People, Stimuli, or Targets: Which Semantic Roles Enable Machine Learning to Infer Emotions?,” in Proceedings of the Third Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media, Barcelona, Spain, 2020.
    [BibTeX]
    @inproceedings{Oberlaender2020b,
    added-at = {2020-10-20T10:38:36.000+0200},
    address = {Barcelona, Spain},
    author = {Oberl\"ander, Laura and Reich, Kevin and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/250c9b24bb6914c00ffaf875d6f78420e/dr.romanklinger},
    booktitle = {Proceedings of the Third Workshop on Computational Modeling of People{'}s Opinions, Personality, and Emotions in Social Media},
    interhash = {6f5e25bdee9ba879109446b1e551aa00},
    intrahash = {50c9b24bb6914c00ffaf875d6f78420e},
    keywords = {sentiment nlp myown emotion stimulus cause},
    month = {12},
    publisher = {Association for Computational Linguistics},
    timestamp = {2020-10-20T10:38:36.000+0200},
    title = {Emotional People, Stimuli, or Targets: Which
    Semantic Roles Enable Machine Learning to Infer
    Emotions?},
    year = 2020
    }

  • L. Oberländer and R. Klinger, “Token Sequence Labeling vs. Clause Classification for English Emotion Stimulus Detection,” in Proceedings of the 9th Joint Conferene on Lexical and Computational Semantics, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{Oberlaender2020,
    added-at = {2020-10-08T17:43:32.000+0200},
    author = {Oberl\"ander, Laura and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25996dcbbe5ef732b4f20c3fe54de6276/dr.romanklinger},
    booktitle = {Proceedings of the 9th Joint Conferene on Lexical and Computational Semantics},
    interhash = {59bc23f49072063700e6115b2d7430ab},
    intrahash = {5996dcbbe5ef732b4f20c3fe54de6276},
    keywords = {sentiment nlp myown emotion},
    timestamp = {2020-10-20T10:37:43.000+0200},
    title = {Token Sequence Labeling vs. Clause Classification for English Emotion Stimulus Detection},
    url = {https://arxiv.org/pdf/2010.07557.pdf},
    year = 2020
    }

  • J. Pagel and N. Reiter, “GerDraCor-Coref: A Coreference Corpus for Dramatic Texts in German,” in Proceedings of the Language Resources and Evaluation Conference (LREC), 2020, pp. 55-64.
    [BibTeX] [Abstract] [Download PDF]

    Dramatic texts are a highly structured literary text type. Their quantitative analysis so far has relied on analysing structural properties (e.g., in the form of networks). Resolving coreferences is crucial for an analysis of the content of the character speech, but developing automatic coreference resolution (CR) systems depends on the existence of annotated corpora. In this paper, we present an annotated corpus of German dramatic texts, a preliminary analysis of the corpus as well as some baseline experiments on automatic CR. The analysis shows that with respect to the reference structure, dramatic texts are very different from news texts, but more similar to other dialogical text types such as interviews. Baseline experiments show a performance of 28.8 CoNLL score achieved by the rule-based CR system CorZu. In the future, we plan to integrate the (partial) information given in the dramatis personae into the CR model.

    @inproceedings{pagel2020a,
    abstract = {Dramatic texts are a highly structured literary text type. Their quantitative analysis so far has relied on analysing structural properties (e.g., in the form of networks). Resolving coreferences is crucial for an analysis of the content of the character speech, but developing automatic coreference resolution (CR) systems depends on the existence of annotated corpora. In this paper, we present an annotated corpus of German dramatic texts, a preliminary analysis of the corpus as well as some baseline experiments on automatic CR. The analysis shows that with respect to the reference structure, dramatic texts are very different from news texts, but more similar to other dialogical text types such as interviews. Baseline experiments show a performance of 28.8 CoNLL score achieved by the rule-based CR system CorZu. In the future, we plan to integrate the (partial) information given in the dramatis personae into the CR model.},
    added-at = {2020-05-14T23:25:41.000+0200},
    author = {Pagel, Janis and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e8d62d19a8a3bede573fac66db7f0ffe/janispagel},
    booktitle = {Proceedings of the Language Resources and Evaluation Conference (LREC)},
    interhash = {343065b3de90bb9423a9f8c4346f31b9},
    intrahash = {e8d62d19a8a3bede573fac66db7f0ffe},
    keywords = {myown},
    language = {en},
    location = {Marseille, France},
    month = {05},
    pages = {55-64},
    timestamp = {2020-05-21T10:54:16.000+0200},
    title = {GerDraCor-Coref: A Coreference Corpus for Dramatic Texts in German},
    url = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.7.pdf},
    venue = {Marseille, France},
    year = 2020
    }

  • J. Pagel, N. Reiter, I. Rösiger, and S. Schulz, “Annotation als flexibel einsetzbare Methode,” in Reflektierte Algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt, N. Reiter, A. Pichler, and J. Kuhn, Eds., Berlin: De Gruyter, 2020, p. 125–142. doi:10.1515/9783110693973-006
    [BibTeX]
    @incollection{pagel2020b,
    added-at = {2020-08-10T23:41:28.000+0200},
    address = { Berlin },
    author = {Pagel, Janis and Reiter, Nils and Rösiger, Ina and Schulz, Sarah},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2ec9eef2f860f2132f74fc8f43534b161/janispagel},
    booktitle = {Reflektierte Algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    doi = {10.1515/9783110693973-006},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {2fcc42cfee5f84334ed52cfd50b511b5},
    intrahash = {ec9eef2f860f2132f74fc8f43534b161},
    keywords = {annotation myown creta},
    pages = {125--142},
    publisher = {De Gruyter},
    timestamp = {2020-08-10T23:41:28.000+0200},
    title = {Annotation als flexibel einsetzbare Methode},
    year = 2020
    }

  • S. Papay and S. Padó, “RiQuA: A Corpus of Rich Quotation Annotation for English Literary Text,” in Proceedings of LREC, Online, 2020, p. 835–841.
    [BibTeX] [Abstract] [Download PDF]

    We introduce RiQuA (RIch QUotation Annotations), a corpus that provides quotations, including their interpersonal structure (speakers and addressees) for English literary text. The corpus comprises 11 works of 19th-century literature that were manually doubly annotated for direct and indirect quotations. For each quotation, its span, speaker, addressee, and cue are identified (if present). This provides a rich view of dialogue structures not available from other available corpora. We detail the process of creating this dataset, discuss the annotation guidelines, and analyze the resulting corpus in terms of inter-annotator agreement and its properties. RiQuA, along with its annotations guidelines and associated scripts, are publicly available for use, modification, and experimentation.

    @inproceedings{papay2020riqua,
    abstract = {We introduce RiQuA (RIch QUotation Annotations), a corpus that provides quotations, including their interpersonal structure (speakers and addressees) for English literary text. The corpus comprises 11 works of 19th-century literature that were manually doubly annotated for direct and indirect quotations. For each quotation, its span, speaker, addressee, and cue are identified (if present). This provides a rich view of dialogue structures not available from other available corpora. We detail the process of creating this dataset, discuss the annotation guidelines, and analyze the resulting corpus in terms of inter-annotator agreement and its properties. RiQuA, along with its annotations guidelines and associated scripts, are publicly available for use, modification, and experimentation.},
    added-at = {2020-02-11T14:44:55.000+0100},
    address = {Online},
    author = {Papay, Sean and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2a9bd0260c8935a0af9ed87270e0caf05/sp},
    booktitle = {Proceedings of LREC},
    interhash = {0f266b20bfd4e958e7f946dbc1cea8ea},
    intrahash = {a9bd0260c8935a0af9ed87270e0caf05},
    keywords = {myown conference},
    pages = {835--841},
    timestamp = {2020-12-07T16:42:29.000+0100},
    title = {{RiQuA}: A Corpus of Rich Quotation Annotation for English Literary Text},
    url = {https://www.aclweb.org/anthology/2020.lrec-1.104},
    year = 2020
    }

  • N. Reiter, G. Kremer, K. Jung, B. Krautter, J. Pagel, and A. Pichler, “Reaching out: Interdisziplinäre Kommunikation und Dissemination,” in Reflektierte Algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt, N. Reiter, A. Pichler, and J. Kuhn, Eds., Berlin: De Gruyter, 2020, p. 467–484. doi:10.1515/9783110693973-019
    [BibTeX]
    @incollection{reiter2020a,
    added-at = {2020-08-10T23:42:41.000+0200},
    address = { Berlin },
    author = {Reiter, Nils and Kremer, Gerhard and Jung, Kerstin and Krautter, Benjamin and Pagel, Janis and Pichler, Axel},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2b596e141bc17faceb1bf5cd7a46f5ea0/janispagel},
    booktitle = {Reflektierte Algorithmische Textanalyse. Interdisziplinäre(s) Arbeiten in der CRETA-Werkstatt},
    doi = {10.1515/9783110693973-019},
    editor = {Reiter, Nils and Pichler, Axel and Kuhn, Jonas},
    interhash = {71928fe362de1c6dc10b7b7e4534e364},
    intrahash = {b596e141bc17faceb1bf5cd7a46f5ea0},
    keywords = {myown creta},
    pages = {467--484},
    publisher = {De Gruyter},
    timestamp = {2020-08-10T23:42:41.000+0200},
    title = {Reaching out: Interdisziplinäre Kommunikation und Dissemination},
    year = 2020
    }

  • D. Schlechtweg, B. McGillivray, S. Hengchen, H. Dubossarsky, and N. Tahmasebi, “SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection,” in Proceedings of the 14th International Workshop on Semantic Evaluation, Barcelona, Spain, 2020.
    [BibTeX] [Download PDF]
    @inproceedings{schlechtweg2020semeval,
    added-at = {2020-09-15T10:44:06.000+0200},
    address = {Barcelona, Spain},
    author = {Schlechtweg, Dominik and McGillivray, Barbara and Hengchen, Simon and Dubossarsky, Haim and Tahmasebi, Nina},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2cccf7bc34d3aea7b1cd8e80265ab150a/dschlechtweg},
    booktitle = {Proceedings of the 14th International Workshop on Semantic Evaluation},
    interhash = {eac491c1e765ee81acb7980ca07a0602},
    intrahash = {cccf7bc34d3aea7b1cd8e80265ab150a},
    keywords = {myown},
    publisher = {Association for Computational Linguistics},
    timestamp = {2020-09-15T10:48:56.000+0200},
    title = {{S}em{E}val-2020 {T}ask 1: {U}nsupervised {L}exical {S}emantic {C}hange {D}etection},
    url = {https://arxiv.org/abs/2007.11464},
    year = 2020
    }

  • D. Schlechtweg and S. Schulte im Walde, “Simulating Lexical Semantic Change from Sense-Annotated Data,” in The Evolution of Language: Proceedings of the 13th International Conference (EvoLang13), 2020. doi:10.17617/2.3190925
    [BibTeX] [Download PDF]
    @inproceedings{SchlechtwegWalde20,
    added-at = {2020-03-17T01:11:57.000+0100},
    author = {Schlechtweg, Dominik and Schulte im Walde, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20a7ce238903527c61fc2352f7affda29/dschlechtweg},
    booktitle = {The Evolution of Language: Proceedings of the 13th International Conference (EvoLang13)},
    doi = {10.17617/2.3190925},
    editor = {Ravignani, A. and Barbieri, C. and Martins, M. and Flaherty, M. and Jadoul, Y. and Lattenkamp, E. and Little, H. and Mudd, K. and Verhoef, T.},
    interhash = {6ff88aadeaf8f2ab9a89665585b653db},
    intrahash = {0a7ce238903527c61fc2352f7affda29},
    keywords = {myown},
    timestamp = {2020-03-17T01:16:43.000+0100},
    title = {Simulating Lexical Semantic Change from Sense-Annotated Data},
    url = {http://brussels.evolang.org/proceedings/paper.html?nr=9},
    year = 2020
    }

  • N. Wiedmer, J. Pagel, and N. Reiter, “Romeo, Freund des Mercutio: Semi-Automatische Extraktion von Beziehungen zwischen dramatischen Figuren,” in Book of Abstracts of DHd, 2020, pp. 194-200. doi:10.5281/zenodo.3666690
    [BibTeX] [Abstract]

    In diesem Beitrag stellen wir eine Methode vor, um Informationen über Figurenrelationen in dramatischen Texten, die innerhalb der dramatis personae (Figurenverzeichnis) sprachlich kodiert sind, zu extrahieren und maschinenlesbar im TEI/XML vorzuhalten Das Verfahren ist auch für in Zukunft digitalisierte Dramen anwendbar, und wird von uns als quelloffene Software zur Verfügung gestellt. Es ist vergleichsweise einfach auf neue Sprachstufen oder Genres anpassbar und liefert eine gute Vorlage. Eine Evaluation des Verfahrens erfolgt auf ungesehenen Testdaten. Außerdem veröffentlichen wir einen Datensatz mit extrahierten Figurenrelationen aus deutschsprachigen Dramen, die manuell validiert und korrigiert wurden. Diese Daten werden zur einfachen und breiten Nutzung im TEI-Format in das GerDraCor eingespeist. Schlussendlich beschreiben wir beispielhaft zwei Analyseszenarien in denen die Daten neue Einblicke bieten (können).

    @inproceedings{wiedmer2020a,
    abstract = {In diesem Beitrag stellen wir eine Methode vor, um Informationen über Figurenrelationen in dramatischen Texten, die innerhalb der dramatis personae (Figurenverzeichnis) sprachlich kodiert sind, zu extrahieren und maschinenlesbar im TEI/XML vorzuhalten
    Das Verfahren ist auch für in Zukunft digitalisierte Dramen anwendbar, und wird von uns als quelloffene Software zur Verfügung gestellt. Es ist vergleichsweise einfach auf neue Sprachstufen oder Genres anpassbar und liefert eine gute Vorlage. Eine Evaluation des Verfahrens erfolgt auf ungesehenen Testdaten. Außerdem veröffentlichen wir einen Datensatz mit extrahierten Figurenrelationen aus deutschsprachigen Dramen, die manuell validiert und korrigiert wurden. Diese Daten werden zur einfachen und breiten Nutzung im TEI-Format in das GerDraCor eingespeist. Schlussendlich beschreiben wir beispielhaft zwei Analyseszenarien in denen die Daten neue Einblicke bieten (können).},
    added-at = {2020-05-14T23:23:14.000+0200},
    author = {Wiedmer, Nathalie and Pagel, Janis and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2ad6d0c573d5b5cff21910b8f21b657ed/janispagel},
    booktitle = {Book of Abstracts of DHd},
    doi = {10.5281/zenodo.3666690},
    editor = {Schöch, Christof},
    interhash = {0b751cd6e9f7b55740e54f67f1c5866d},
    intrahash = {ad6d0c573d5b5cff21910b8f21b657ed},
    keywords = {myown},
    language = {de},
    location = {Paderborn, Germany},
    month = {03},
    pages = {194-200},
    timestamp = {2020-05-21T10:54:27.000+0200},
    title = {Romeo, Freund des Mercutio: Semi-Automatische Extraktion von Beziehungen zwischen dramatischen Figuren},
    venue = {Paderborn, Germany},
    year = 2020
    }

  • M. Willand, B. Krautter, J. Pagel, and N. Reiter, “Passive Präsenz tragischer Hauptfiguren im Drama,” in Book of Abstracts of DHd, 2020, pp. 177-181. doi:10.5281/zenodo.3666690
    [BibTeX] [Abstract]

    Der Vortrag stellt einen Versuch vor, Figurenpräsenz in dramatischen Texten auch als “passive Präsenz” zu modellieren, d.h. greifbar zu machen, dass gerade auf Hauptfiguren auf sehr unterschiedliche Weise referiert wird, wenn diese gerade nicht selbst handeln. Dazu stellen wir eine Operationalisierung von „passiver Präsenz“ vor und vergleichen die aktive und passive Präsenz von Hauptfiguren in unterschiedlichen dramatischen Gernres und Epochen. Die identifizierbare gattungsspezifische Präsenzgestaltung von Hauptfiguren lässt auf grundlegend divergierende Bauprinzipien dramatischer Text schließen. Da diese Unterschiede beim linearen Lesen jedoch kaum sichtbar sind, möchte dieser Forschungsbeitrag als Argument für die Erweiterung der qualitativ-interpretierenden Dramenanalyse durch quantitative Methoden verstanden werden.

    @inproceedings{willand2020a,
    abstract = {Der Vortrag stellt einen Versuch vor, Figurenpräsenz in dramatischen Texten auch als “passive Präsenz” zu modellieren, d.h. greifbar zu machen, dass gerade auf Hauptfiguren auf sehr unterschiedliche Weise referiert wird, wenn diese gerade nicht selbst handeln. Dazu stellen wir eine Operationalisierung von „passiver Präsenz“ vor und vergleichen die aktive und passive Präsenz von Hauptfiguren in unterschiedlichen dramatischen Gernres und Epochen. Die identifizierbare gattungsspezifische Präsenzgestaltung von Hauptfiguren lässt auf grundlegend divergierende Bauprinzipien dramatischer Text schließen. Da diese Unterschiede beim linearen Lesen jedoch kaum sichtbar sind, möchte dieser Forschungsbeitrag als Argument für die Erweiterung der qualitativ-interpretierenden Dramenanalyse durch quantitative Methoden verstanden werden.},
    added-at = {2020-05-14T23:21:05.000+0200},
    author = {Willand, Marcus and Krautter, Benjamin and Pagel, Janis and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2de38d9c29b1e7d8eb39572f3ed41889b/janispagel},
    booktitle = {Book of Abstracts of DHd},
    doi = {10.5281/zenodo.3666690},
    editor = {Schöch, Christof},
    interhash = {f1cc3020a43de2b353f78993c51522ed},
    intrahash = {de38d9c29b1e7d8eb39572f3ed41889b},
    keywords = {myown},
    language = {de},
    location = {Paderborn, Germany},
    month = {03},
    pages = {177-181},
    timestamp = {2020-05-14T23:37:51.000+0200},
    title = {Passive Präsenz tragischer Hauptfiguren im Drama},
    venue = {Paderborn, Germany},
    year = 2020
    }

2019

  • M. Baumann, M. John, H. Pflüger, C. Herberichs, G. Viehhauser, W. Knopki, and T. Ertl, “An Interactive Visualization for the Analysis of Annotated Text Variance in the Legendary Der Heiligen Leben, Redaktion,” in Leipzig Symp. Vis. App. (LEVIA ’19), 2019. doi:10.31219/osf.io/wd9yz
    [BibTeX]
    @inproceedings{Baumann.2019e,
    added-at = {2020-03-30T23:36:28.000+0200},
    author = {Baumann, Martin and John, Markus and Pfl{\"u}ger, Hermann and Herberichs, Cornelia and Viehhauser, Gabriel and Knopki, Wolfgang and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/27369a88f17921ce95c592b578d25fba7/martinbaumann},
    booktitle = {Leipzig Symp. Vis. App. (LEVIA '19)},
    doi = {10.31219/osf.io/wd9yz},
    interhash = {c66d8a90fd811cebdb6cd9050129dae1},
    intrahash = {7369a88f17921ce95c592b578d25fba7},
    keywords = {myown vis-gis vis(us) visus:pflueghn visus:ertl visus:baumanmn visus:johnms},
    timestamp = {2020-03-30T23:38:33.000+0200},
    title = {{An Interactive Visualization for the Analysis of Annotated Text Variance in the Legendary Der Heiligen Leben, Redaktion}},
    year = 2019
    }

  • A. Blessing, N. Blokker, S. Haunss, J. Kuhn, G. Lapesa, and S. Padó, “An Environment for the Relational Annotation of Political Debates,” in Proceedings of ACL System Demonstrations, Florence, Italy, 2019.
    [BibTeX] [Abstract] [Download PDF]

    This paper describes the MARDY corpus annotation environment developed for a collaboration between political science and computational linguistics. The tool realizes the complete workflow necessary for annotating a large newspaper text collection with rich information about claims (demands) raised by politicians and other actors, including claim and actor spans, relations, and polarities. In addition to the annotation GUI, the tool supports the identification of relevant documents, text pre-processing, user management, integration of external knowledge bases, annotation comparison and merging, statistical analysis, and the incorporation of machine learning models as “pseudo-annotators”.

    @inproceedings{blessing19:_envir_relat_annot_polit_debat,
    abstract = {This paper describes the MARDY corpus annotation environment
    developed for a collaboration
    between political science and computational linguistics. The tool realizes the complete workflow necessary for annotating a large newspaper text collection with rich information about claims (demands) raised by politicians and other actors, including claim and actor spans, relations, and polarities. In addition to the annotation GUI, the tool supports the identification of relevant documents, text pre-processing, user management, integration of external knowledge bases, annotation comparison and merging, statistical analysis, and the incorporation of machine learning models as "pseudo-annotators".},
    added-at = {2019-05-19T19:35:20.000+0200},
    address = {Florence, Italy},
    author = {Blessing, André and Blokker, Nico and Haunss, Sebastian and Kuhn, Jonas and Lapesa, Gabriella and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2eaa29a7bb230baf086024e12440c9f2d/sp},
    booktitle = {Proceedings of ACL System Demonstrations},
    interhash = {b4b9d5748254001be40db3ae0df098f3},
    intrahash = {eaa29a7bb230baf086024e12440c9f2d},
    keywords = {myown conference},
    timestamp = {2019-07-29T21:51:12.000+0200},
    title = {An Environment for the Relational Annotation of Political Debates},
    url = {https://aclweb.org/anthology/papers/P/P19/P19-3018/},
    year = 2019
    }

  • L. A. M. Bostan and R. Klinger, “Exploring Fine-Tuned Embeddings that Model Intensifiers for Emotion Analysis,” in Proceedings of the 10th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Minneapolis, USA, 2019.
    [BibTeX]
    @inproceedings{Bostan2019,
    added-at = {2019-05-14T14:55:31.000+0200},
    address = {Minneapolis, USA},
    author = {Bostan, Laura Ana Maria and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c9cb244138ed00a8b778e46c0ed0a707/dr.romanklinger},
    booktitle = {Proceedings of the 10th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {47f63d69c1e0e9a76a32ebbd328e2488},
    intrahash = {c9cb244138ed00a8b778e46c0ed0a707},
    keywords = {sentiment myown emotion},
    month = {06},
    organization = {Association for Computational Linguistics},
    pdf = {http://www.romanklinger.de/publications/bostan2018.pdf},
    timestamp = {2020-05-14T11:07:43.000+0200},
    title = {Exploring Fine-Tuned Embeddings that Model Intensifiers for Emotion Analysis},
    year = 2019
    }

  • M. Braun and N. Ketschik, “Soziale Netzwerkanalysen zum mittelhochdeutschen Artusroman – oder: Vorgreiflicher Versuch, Märchenhaftigkeit des Erzählens zu messen,” Das Mittelalter, vol. 24, iss. 1, pp. 54-70, 2019. doi:https://doi.org/10.1515/mial-2019-0005
    [BibTeX] [Abstract]

    This article discusses the question of how complex the narrations of Arthurian romances are by comparing them to the ‘simple form’ of fairy tales. In order to achieve this, we identify properties of the European folktale, which we then compare with an Arthurian text corpus consisting of Hartmann von Aue’s ‘Erec’ and ‘Iwein’ as well as Wolfram von Eschenbach’s ‘Parzival’. The typological investigation is carried out using data-driven methods, primarily Social Network Analysis, and focuses on various aspects of characters. By doing this, we gain an in-depth understanding of the relationships between Arthurian romances and fairy tales and of the differences within the genre of the Arthurian romance itself. We show that the results of statistical analysis refuse clear interpretation, thus providing new insights into the well-known objects.

    @article{braun2019soziale,
    abstract = {This article discusses the question of how complex the narrations of
    Arthurian romances are by comparing them to the ‘simple form’ of fairy tales. In
    order to achieve this, we identify properties of the European folktale, which we
    then compare with an Arthurian text corpus consisting of Hartmann von Aue’s
    ‘Erec’ and ‘Iwein’ as well as Wolfram von Eschenbach’s ‘Parzival’. The typological
    investigation is carried out using data-driven methods, primarily Social Network
    Analysis, and focuses on various aspects of characters. By doing this, we gain an
    in-depth understanding of the relationships between Arthurian romances and fairy
    tales and of the differences within the genre of the Arthurian romance itself. We
    show that the results of statistical analysis refuse clear interpretation, thus providing
    new insights into the well-known objects.},
    added-at = {2020-03-23T20:54:12.000+0100},
    author = {Braun, Manuel and Ketschik, Nora},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/20802cb4a9ebf032dc5ca08af5ec3babd/nora-ketschik},
    doi = {https://doi.org/10.1515/mial-2019-0005},
    interhash = {bc341676a15eb3b524c9f47e3e2f5d1a},
    intrahash = {0802cb4a9ebf032dc5ca08af5ec3babd},
    journal = {Das Mittelalter},
    keywords = {SocialNetzworkAnalysis Middle-High-German},
    number = 1,
    pages = {54-70},
    timestamp = {2020-03-23T21:10:32.000+0100},
    title = {Soziale Netzwerkanalysen zum mittelhochdeutschen Artusroman - oder: Vorgreiflicher Versuch, Märchenhaftigkeit des Erzählens zu messen},
    volume = 24,
    year = 2019
    }

  • H. Ehrlicher, R. Klinger, J. Lehmann, and S. Padó, “Measuring Historical Emotions and Their Evolution: An Interdisciplinary Endeavour to Investigate The ‘Emotions of Encounter’,” Liinc Em Revista, vol. 15, iss. 1, p. 70–84, 2019.
    [BibTeX] [Abstract] [Download PDF]

    The empirical study of emotions in Spanish travelogues and reports requires cultural knowledge as well as the use of linguistic annotation and quantitative methods. We report on an interdisciplinary project in which we perform emotion annotation on a selection of texts spanning several centuries to analyze the differences across different time slices. We show that indeed the emotional connotation changes qualitatively and quantitatively. Next to this evaluation, we sketch strategies for future automation. This scalable reading approach combines quantitative with qualitative insights and identifies developments over time that call for deeper investigation.

    @article{ehrlicher19:_measur_histor_emotion_their_evolut,
    abstract = {The empirical study of emotions in Spanish travelogues and reports requires cultural knowledge as well as the use of linguistic annotation and quantitative methods. We report on an interdisciplinary project in which we perform emotion annotation on a selection of texts spanning several centuries to analyze the differences across different time slices. We show that indeed the emotional connotation changes qualitatively and quantitatively. Next to this evaluation, we sketch strategies for future automation. This scalable reading approach combines quantitative with qualitative insights and identifies developments over time that call for deeper investigation.},
    added-at = {2019-06-29T21:04:52.000+0200},
    author = {Ehrlicher, Hanno and Klinger, Roman and Lehmann, Jörg and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/240d5b545a423095ddc4737c9586df1f6/sp},
    description = {https://doi.org/10.18617/liinc.v15i1.4557},
    interhash = {47351f4f708b39722bab706880ce93cb},
    intrahash = {40d5b545a423095ddc4737c9586df1f6},
    journal = {Liinc Em Revista},
    keywords = {myown article},
    number = 1,
    pages = {70--84},
    timestamp = {2020-04-21T15:07:16.000+0200},
    title = {Measuring Historical Emotions and Their Evolution: An Interdisciplinary Endeavour to Investigate The ‘Emotions of Encounter’},
    url = {http://revista.ibict.br/liinc/article/view/4557},
    volume = 15,
    year = 2019
    }

  • H. Ehrlicher, R. Klinger, J. Lehmann, and S. Padó, “Measuring Historical Emotions and Their Evolution: An Interdisciplinary Endeavour to Investigate The `Emotions of Encounter’,” Laboratório Interdisciplinar sobre Informa\,cão e Conhecimento em revista (Liinc em revista), vol. 15, iss. 1, 2019. doi:10.18617/liinc.v15i1.4557
    [BibTeX] [Download PDF]
    @article{Ehrlicher2019,
    added-at = {2019-06-29T13:31:53.000+0200},
    author = {Ehrlicher, Hanno and Klinger, Roman and Lehmann, J\"org and Pad\'o, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/285fef69f64dda7717c40aa5ba9f89f44/dr.romanklinger},
    doi = {10.18617/liinc.v15i1.4557},
    interhash = {544f87513a4a90e259ad8535d8cd20af},
    intrahash = {85fef69f64dda7717c40aa5ba9f89f44},
    journal = {Laborat\'orio Interdisciplinar sobre Informa\,{c}\~{a}o e Conhecimento em revista (Liinc em revista)},
    keywords = {nlp myown digitalhumanities emotion},
    number = 1,
    pdf = {http://revista.ibict.br/liinc/article/download/4557/4140},
    timestamp = {2019-06-29T13:31:53.000+0200},
    title = {Measuring Historical Emotions and Their Evolution: An Interdisciplinary Endeavour to Investigate The `Emotions of Encounter'},
    url = {http://revista.ibict.br/liinc/issue/view/275},
    volume = 15,
    year = 2019
    }

  • S. Haunss, N. Blokker, S. Pado, J. Kuhn, A. Blessing, G. Lapesa, and E. Dayanik, “Supporting Discourse Network Analysis through Machine Learning for Claim Detection and Classification,” in Proceedings of the 4th European Conference on Social Networks, Zurich, Switzerland, 2019.
    [BibTeX]
    @inproceedings{sebastian19:_suppor_discour_networ_analy_machin,
    added-at = {2019-06-03T09:28:39.000+0200},
    address = {Zurich, Switzerland},
    author = {Haunss, Sebastian and Blokker, Nico and Pado, Sebastian and Kuhn, Jonas and Blessing, Andre and Lapesa, Gabriella and Dayanik, Erenay},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2847651334e3609079a954b98a811338b/sp},
    booktitle = {Proceedings of the 4th European Conference on Social Networks},
    interhash = {f3bfc165a77a00f85a13605194644040},
    intrahash = {847651334e3609079a954b98a811338b},
    keywords = {myown abstract},
    timestamp = {2021-03-08T21:06:35.000+0100},
    title = {Supporting Discourse Network Analysis through Machine Learning for Claim Detection and Classification},
    year = 2019
    }

  • M. John, M. Baumann, D. Schuetz, S. Koch, and T. Ertl, “A Visual Approach for the Comparative Analysis of Character Networks in Narrative Texts,” in Proc. IEEE Pac. Vis. Symp. (PacificVis), 2019, p. 247–256.
    [BibTeX]
    @inproceedings{John.2019,
    added-at = {2019-08-09T11:50:36.000+0200},
    author = {John, Markus and Baumann, Martin and Schuetz, David and Koch, Steffen and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2bbbdf5b30f693f35be438942ffbddfb2/martinbaumann},
    booktitle = {Proc. IEEE Pac. Vis. Symp. (PacificVis)},
    interhash = {dcbcd9a30d3906f41c918efffe4e7f3c},
    intrahash = {bbbdf5b30f693f35be438942ffbddfb2},
    keywords = {vis-gis vis(us) visus:kochsn visus:ertl visus:baumanmn visus:johnms},
    pages = {247--256},
    timestamp = {2019-08-09T11:50:36.000+0200},
    title = {{A Visual Approach for the Comparative Analysis of Character Networks in Narrative Texts}},
    year = 2019
    }

  • N. Ketschik, B. Krautter, S. Murr, and Y. Zimmermann, “Annotation Guideline No. 4: Annotating Narrative Levels in Literature,” Journal of Cultural Analytics, 2019.
    [BibTeX]
    @article{ketschik2019annotation,
    added-at = {2020-10-16T11:24:29.000+0200},
    author = {Ketschik, Nora and Krautter, Benjamin and Murr, Sandra and Zimmermann, Yvonne},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/205b1214c71e3f97b1f44148a31d0c591/noraketschik},
    interhash = {dc43eda424d33cf74d0d93ea85550eec},
    intrahash = {05b1214c71e3f97b1f44148a31d0c591},
    journal = {Journal of Cultural Analytics},
    keywords = {annotation myown dh narratology},
    timestamp = {2020-10-19T10:42:20.000+0200},
    title = {Annotation Guideline No. 4: Annotating Narrative Levels in Literature},
    year = 2019
    }

  • E. Kim and R. Klinger, “An Analysis of Emotion Communication Channels in Fan-Fiction: Towards Emotional Storytelling,” in Proceedings of the Second Workshop of Storytelling, 2019.
    [BibTeX]
    @inproceedings{Kim2019a,
    added-at = {2019-06-29T13:32:29.000+0200},
    author = {Kim, Evgeny and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2eaec7728bb9f431c00422a8d4d8869bb/dr.romanklinger},
    booktitle = {Proceedings of the Second Workshop of Storytelling},
    interhash = {701d1c75264af2fe2eda690401beaea1},
    intrahash = {eaec7728bb9f431c00422a8d4d8869bb},
    keywords = {sentiment myown digitalhumanities emotion},
    organization = {Association for Computational Linguistics},
    pdf = {http://www.romanklinger.de/publications/KimKlingerStoryNLP2019ACL.pdf},
    timestamp = {2019-06-29T13:32:29.000+0200},
    title = {An Analysis of Emotion Communication Channels in Fan-Fiction: Towards Emotional Storytelling},
    year = 2019
    }

  • E. Kim and R. Klinger, “Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters,” in Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, USA, 2019.
    [BibTeX] [Download PDF]
    @inproceedings{Kim2019,
    added-at = {2019-02-28T16:33:56.000+0100},
    address = {Minneapolis, USA},
    author = {Kim, Evgeny and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e805a1ea4b7018e3375522f521ad78f9/dr.romanklinger},
    booktitle = {Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics},
    interhash = {e65d72af4aa7a7b9bb374d8667d5b037},
    intrahash = {e805a1ea4b7018e3375522f521ad78f9},
    keywords = {literature sentiment nlp myown digitalhumanities emotion dh relationextraction},
    month = {06},
    organization = {Association for Computational Linguistics},
    timestamp = {2019-03-29T12:31:57.000+0100},
    title = {{Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters}},
    url = {http://www.romanklinger.de/publications/KimKlingerNAACL2019.pdf},
    year = 2019
    }

  • G. Kremer and K. Jung, “Maschinelles Lernen lernen: Ein CRETA-Hackatorial zur reflektierten automatischen Textanalyse,” in DHd 2019 Digital Humanities: multimedial & multimodal. Conference abstracts, Frankfurt am Main, Germany, 2019, p. 36–39.
    [BibTeX] [Download PDF]
    @inproceedings{KremerJungDHd19:MaschLern,
    added-at = {2019-04-09T17:43:33.000+0200},
    address = {Frankfurt am Main, Germany},
    author = {Kremer, Gerhard and Jung, Kerstin},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29407f12426471f199f33fff14be7f9c4/drgerhardkremer},
    booktitle = {DHd 2019 Digital Humanities: multimedial \& multimodal. Conference abstracts},
    editor = {Sahle, Patrick},
    interhash = {df24f19a735a1c658bbfd94d07636c20},
    intrahash = {9407f12426471f199f33fff14be7f9c4},
    keywords = {myown},
    language = {German},
    month = {03},
    pages = {36--39},
    publisher = {Zenodo},
    timestamp = {2020-02-08T00:08:15.000+0100},
    title = {Maschinelles {L}ernen lernen: {E}in {CRETA}-{H}ackatorial zur reflektierten automatischen {T}extanalyse},
    url = {https://doi.org/10.5281/zenodo.2600812},
    year = 2019
    }

  • S. Padó, A. Blessing, N. Blokker, E. Dayanik, S. Haunss, and J. Kuhn, “Who Sides With Whom? Towards Computational Construction of Discourse Networks for Political Debates,” in Proceedings of ACL, Florence, Italy, 2019.
    [BibTeX] [Abstract] [Download PDF]

    Understanding the structures of political debates (which actors make what claims) is essential for understanding democratic political decision-making. The vision of computational construction of such \textit{discourse networks} from newspaper reports brings together political science and natural language processing. This paper presents three contributions towards this goal: (a) a requirements analysis, linking the task to knowledge base population; (b) a first release of an annotated corpus of claims on the topic of migration, based on German newspaper reports; (c) initial modeling results.

    @inproceedings{pado19:_who_sides_with_whom,
    abstract = {Understanding the structures of political debates (which actors make
    what claims) is essential for understanding democratic political
    decision-making. The vision of computational construction of such
    \textit{discourse networks} from newspaper reports brings together
    political science and natural language processing. This paper
    presents three contributions towards this goal: (a) a requirements
    analysis, linking the task to knowledge base population;
    (b) a first release of an annotated corpus of
    claims on the topic of migration, based on German newspaper reports; (c) initial modeling results.},
    added-at = {2019-05-14T12:02:03.000+0200},
    address = {Florence, Italy},
    author = {Padó, Sebastian and Blessing, André and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2483e9bdc5e88e4c647137a437739d49a/sp},
    booktitle = {Proceedings of ACL},
    interhash = {4f32326209adb681faaf38dc6919e57f},
    intrahash = {483e9bdc5e88e4c647137a437739d49a},
    keywords = {imported myown conference},
    timestamp = {2019-07-29T21:47:50.000+0200},
    title = {Who Sides With Whom? Towards Computational Construction of Discourse Networks for Political Debates},
    url = {https://aclweb.org/anthology/papers/P/P19/P19-1273/},
    year = 2019
    }

  • M. Riedl, D. Betz, and S. Padó, “Clustering-Based Article Identification in Historical Newspapers,” in Proceedings of the NAACL LaTeCH-CLfL workshop, Minneapolis, MN, 2019.
    [BibTeX] [Download PDF]
    @inproceedings{riedl19:_clust_based_artic_ident_histor_newsp,
    added-at = {2019-03-28T09:58:13.000+0100},
    address = {Minneapolis, MN},
    author = {Riedl, Martin and Betz, Daniela and Padó, Sebastian},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/22b78ff67fb5642f79af0e7de0cb768f4/sp},
    booktitle = {Proceedings of the NAACL LaTeCH-CLfL workshop},
    comment = {Accepted for publication},
    interhash = {9aa2f674b9025d5994b553566041b0ee},
    intrahash = {2b78ff67fb5642f79af0e7de0cb768f4},
    keywords = {myown workshop},
    privnote = {Accepted for publication},
    timestamp = {2019-06-01T20:54:57.000+0200},
    title = {Clustering-Based Article Identification in Historical Newspapers},
    url = {https://aclweb.org/anthology/papers/W/W19/W19-2502/},
    year = 2019
    }

  • D. Schlechtweg, A. Hätty, M. Del Tredici, and S. Schulte im Walde, “A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains.,” in ACL (1), 2019, pp. 732-746.
    [BibTeX] [Download PDF]
    @inproceedings{conf/acl/SchlechtwegHTW19,
    added-at = {2020-01-06T16:27:18.000+0100},
    author = {Schlechtweg, Dominik and Hätty, Anna and Del Tredici, Marco and Schulte im Walde, Sabine},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/266e50b35412aa81fcb8cf955d5df7ddd/dschlechtweg},
    booktitle = {ACL (1)},
    crossref = {conf/acl/2019-1},
    editor = {Korhonen, Anna and Traum, David R. and Màrquez, Lluís},
    ee = {https://www.aclweb.org/anthology/P19-1072/},
    interhash = {eb3a28e88713077e60d1787ec12d9dcd},
    intrahash = {66e50b35412aa81fcb8cf955d5df7ddd},
    isbn = {978-1-950737-48-2},
    keywords = {myown},
    pages = {732-746},
    publisher = {Association for Computational Linguistics},
    timestamp = {2020-03-15T01:39:36.000+0100},
    title = {A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains.},
    url = {https://www.aclweb.org/anthology/P19-1072/},
    year = 2019
    }

  • S. Schulz and N. Ketschik, “From 0 to 10 million annotated words: part-of-speech tagging for Middle High German,” Language Resources and Evaluation, vol. 53, iss. 4, pp. 837-863, 2019.
    [BibTeX] [Abstract] [Download PDF]

    By building a part-of-speech (POS) tagger for Middle High German, we investigate strategies for dealing with a low resource, diverse and non-standard language in the domain of natural language processing. We highlight various aspects such as the data quantity needed for training and the influence of data quality on tagger performance. Since the lack of annotated resources poses a problem for training a tagger, we exemplify how existing resources can be adapted fruitfully to serve as additional training data. The resulting POS model achieves a tagging accuracy of about 91% on a diverse test set representing the different genres, time periods and varieties of MHG.

    @article{schulz2019million,
    abstract = {By building a part-of-speech (POS) tagger for Middle High German, we
    investigate strategies for dealing with a low resource, diverse and non-standard
    language in the domain of natural language processing. We highlight various
    aspects such as the data quantity needed for training and the influence of data
    quality on tagger performance. Since the lack of annotated resources poses a
    problem for training a tagger, we exemplify how existing resources can be adapted
    fruitfully to serve as additional training data. The resulting POS model achieves a
    tagging accuracy of about 91% on a diverse test set representing the different
    genres, time periods and varieties of MHG.},
    added-at = {2020-03-23T21:09:47.000+0100},
    author = {Schulz, Sarah and Ketschik, Nora},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/22be1e9a836990f38d0a186c35c817f13/nora-ketschik},
    interhash = {e0b323aa797abfb88a2505020fe98e04},
    intrahash = {2be1e9a836990f38d0a186c35c817f13},
    journal = {Language Resources and Evaluation},
    keywords = {Middle-High-German POS-Tagging Annotation},
    number = 4,
    pages = {837-863},
    timestamp = {2020-03-23T21:09:47.000+0100},
    title = {From 0 to 10 million annotated words: part-of-speech tagging for Middle High German},
    url = {http://dblp.uni-trier.de/db/journals/lre/lre53.html#SchulzK19},
    volume = 53,
    year = 2019
    }

  • E. Troiano, S. Padó, and R. Klinger, “Crowdsourcing and Validating Event-focused Emotion Corpora for German and English,” in Proceedings of the Annual Conference of the Association for Computational Linguistics, Florence, Italy, 2019.
    [BibTeX]
    @inproceedings{Troiano2019,
    added-at = {2019-05-14T14:54:56.000+0200},
    address = {Florence, Italy},
    author = {Troiano, Enrica and Pad\'o, Sebastian and Klinger, Roman},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2f9a9ae7be6ceddd582c626298eb5b768/dr.romanklinger},
    booktitle = {Proceedings of the Annual Conference of the Association for Computational Linguistics},
    interhash = {dd7f0bb6a940350698d482bac868fd73},
    intrahash = {f9a9ae7be6ceddd582c626298eb5b768},
    keywords = {sentiment nlp myown emotion corpus},
    note = {accepted},
    organization = {Association for Computational Linguistics},
    timestamp = {2019-05-14T14:54:56.000+0200},
    title = {{Crowdsourcing and Validating Event-focused Emotion Corpora for German and English}},
    year = 2019
    }

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 = {literature myown tool dh graph},
    month = {03},
    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
    }

  • M. Baumann, S. Koch, H. Minasyan, and T. Ertl, “Zooming on Tokens: Seamless Display Modes for Annotation Analysis,” in IEEE VIS – Posters, 2018.
    [BibTeX]
    @inproceedings{Baumann.2018,
    added-at = {2019-03-18T10:55:18.000+0100},
    author = {Baumann, Martin and Koch, Steffen and Minasyan, Harutyun and Ertl, Thomas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2efac0909d2cdc1fd3c3a6e67f9540313/martinbaumann},
    booktitle = {IEEE VIS - Posters},
    interhash = {55a0803d30e681373c4b321d3bd6c88f},
    intrahash = {efac0909d2cdc1fd3c3a6e67f9540313},
    keywords = {vis-gis vis(us) visus:kochsn visus:ertl visus:baumanmn},
    note = {Rezensiertes Poster},
    timestamp = {2019-03-18T10:56:35.000+0100},
    title = {{Zooming on Tokens: Seamless Display Modes for Annotation Analysis}},
    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 = {02},
    timestamp = {2017-11-28T12:19:16.000+0100},
    title = {Was Lesende denken: Assoziationen zu Büchern in Sozialen Medien },
    year = 2018
    }

  • A. Blessing and A. Kuczera, “NLP meets RegNLP meets Regesta Imperii,” in Book of Abstracts – Digital Humanities im deutschsprachigen Raum, Cologne, Germany, 2018.
    [BibTeX]
    @inproceedings{Braun2018,
    added-at = {2018-11-05T11:42:49.000+0100},
    address = {Cologne, Germany},
    author = {Blessing, Andre and Kuczera, Andreas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e6fb4e22ef91e5b4945158802e20cddf/blessing},
    booktitle = {Book of Abstracts -- Digital Humanities im deutschsprachigen Raum},
    interhash = {5fc46779662fa60d67ba8fe2626aa807},
    intrahash = {e6fb4e22ef91e5b4945158802e20cddf},
    keywords = {myown},
    month = {03},
    timestamp = {2018-11-05T11:43:12.000+0100},
    title = {{NLP meets RegNLP meets Regesta Imperii}},
    year = 2018
    }

  • A. Blätte and A. Blessing, “The GermaParl Corpus of Parliamentary Protocols,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, 2018.
    [BibTeX]
    @inproceedings{BLÄTTE18.1024,
    added-at = {2018-11-05T11:26:36.000+0100},
    address = {Miyazaki, Japan},
    author = {Blätte, Andreas and Blessing, Andre},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/224c8a897736315cf8cd4f1f41eed2b4b/blessing},
    booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
    editor = {chair), Nicoletta Calzolari (Conference and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, Hélène and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu},
    interhash = {54ae8a5b7dec5bcd33538d7665100e0b},
    intrahash = {24c8a897736315cf8cd4f1f41eed2b4b},
    isbn = {979-10-95546-00-9},
    keywords = {creta},
    language = {english},
    month = {05},
    publisher = {European Language Resources Association (ELRA)},
    timestamp = {2018-11-05T11:26:36.000+0100},
    title = {{The GermaParl Corpus of Parliamentary Protocols}},
    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 = {literature myown dh},
    month = {03},
    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
    }

  • M. Braun and N. Reiter, “Prologe statistisch. Zur Ergänzung qualitativer Zugänge zur Poetologie der mittelhochdeutschen Literatur durch quantitative Analysen,” Zeitschrift für Literaturwissenschaft und Linguistik, vol. 48, iss. 1, pp. 83-103, 2018. doi:10.1007/s41244-017-0081-3
    [BibTeX]
    @article{Braun2018aa,
    added-at = {2018-09-29T09:34:27.000+0200},
    address = { Berlin/Heidelberg, Germany },
    author = {Braun, Manuel and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d476190809faa7e1b06c25f1ce72a4ca/nilsreiter},
    doi = {10.1007/s41244-017-0081-3},
    interhash = {2f362735b3542b6840652d498ba66d4b},
    intrahash = {d476190809faa7e1b06c25f1ce72a4ca},
    journal = { Zeitschrift für Literaturwissenschaft und Linguistik },
    keywords = {myown},
    month = {01},
    number = { 1 },
    pages = { 83-103 },
    publisher = { Springer },
    timestamp = {2018-09-29T09:34:27.000+0200},
    title = {{Prologe statistisch. Zur Ergänzung qualitativer Zugänge zur Poetologie der mittelhochdeutschen Literatur durch quantitative Analysen}},
    volume = { 48 },
    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 = {02},
    timestamp = {2018-10-30T17:51:14.000+0100},
    title = {SANTA: Systematische Analyse Narrativer Texte durch Annotation},
    year = 2018
    }

  • T. Haider and J. Kuhn, “Supervised Rhyme Detection with Siamese Recurrent Networks,” in Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, 2018, p. 81–86.
    [BibTeX] [Download PDF]
    @inproceedings{W18-4509,
    added-at = {2019-02-04T17:43:54.000+0100},
    author = {Haider, Thomas and Kuhn, Jonas},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/213e7e570bc9c04bf7c4f37e5ffc9a1f9/creta},
    booktitle = {Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},
    interhash = {247ac2b33bcda9974f73ea35e60f3d76},
    intrahash = {13e7e570bc9c04bf7c4f37e5ffc9a1f9},
    keywords = {from:drgerhardkremer},
    location = {Santa Fe, New Mexico},
    pages = {81--86},
    publisher = {Association for Computational Linguistics},
    timestamp = {2019-02-04T17:43:54.000+0100},
    title = {Supervised Rhyme Detection with Siamese Recurrent Networks},
    url = {http://aclweb.org/anthology/W18-4509},
    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 = {Visual Visualization, Humanities, Analytics,},
    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 = {myown methods},
    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 = {sentiment nlp myown emotion resource corpus},
    month = {08},
    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
    }

  • R. Klinger, O. de Clercq, S. M. Mohammad, and A. Balahur, “IEST: WASSA-2018 Implicit Emotions Shared Task,” in Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Brussels, Belgium, 2018.
    [BibTeX] [Download PDF]
    @inproceedings{Klinger2018x,
    added-at = {2018-11-15T19:01:35.000+0100},
    address = {Brussels, Belgium},
    author = {Klinger, Roman and de Clercq, Orph\'ee and Mohammad, Saif M. and Balahur, Alexandra},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2b4b991f0be74897453583ea3c58bf9f6/dr.romanklinger},
    booktitle = {Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
    interhash = {a641bedb48165c6e412fca99d2aa29bb},
    intrahash = {b4b991f0be74897453583ea3c58bf9f6},
    keywords = {sentiment nlp myown emotion sharedtask},
    month = {11},
    organization = {Association for Computational Linguistics},
    pdf = {http://implicitemotions.wassa2018.com/paper/iest-description-2018.pdf},
    timestamp = {2018-11-15T19:01:35.000+0100},
    title = {{IEST}: {WASSA}-2018 Implicit Emotions Shared Task},
    url = {http://aclweb.org/anthology/W18-6206},
    year = 2018
    }

  • K. D. Kuthy, N. Reiter, and A. Riester, “QUD-Based Annotation of Discourse Structure and Information Structure: Tool and Evaluation,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, 2018.
    [BibTeX] [Abstract]

    We discuss and evaluate a new annotation scheme and discourse-analytic method, the QUD-tree framework. We present an annotation study, in which the framework, based on the concept of Questions under Discussion, is applied to English and German interview data, using TreeAnno, an annotation tool specially developed for this new kind of discourse annotation. The results of an inter-annotator agreement study show that the new annotation method allows for reasonable agreement with regard to discourse structure and good agreement with regard to the annotation of information structure, which covers focus, background, contrastive topic and non-at-issue material.

    @inproceedings{Kuthy2018aa,
    abstract = {We discuss and evaluate a new annotation scheme and discourse-analytic method, the QUD-tree framework. We present an annotation study, in which the framework, based on the concept of Questions under Discussion, is applied to English and German interview data, using TreeAnno, an annotation tool specially developed for this new kind of discourse annotation. The results of an inter-annotator agreement study show that the new annotation method allows for reasonable agreement with regard to discourse structure and good agreement with regard to the annotation of information structure, which covers focus, background, contrastive topic and non-at-issue material.},
    added-at = {2018-09-29T09:31:43.000+0200},
    address = { Paris, France },
    author = {Kuthy, Kordula De and Reiter, Nils and Riester, Arndt},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/25f538c8159604512040523c9394467b3/nilsreiter},
    booktitle = {{Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}},
    editor = {chair), Nicoletta Calzolari (Conference and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, Hélène and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu},
    interhash = {4c4f3317edf2e3d77b910fd1f2b3e427},
    intrahash = {5f538c8159604512040523c9394467b3},
    isbn = {979-10-95546-00-9},
    keywords = {myown},
    location = {Miyazaki, Japan},
    month = {05},
    publisher = { European Language Resources Association (ELRA) },
    timestamp = {2018-10-30T17:49:43.000+0100},
    title = {{QUD-Based Annotation of Discourse Structure and Information Structure: Tool and Evaluation}},
    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, pp. 231-260.
    [BibTeX] [Download PDF]
    @inbook{overbeck_beobachter,
    added-at = {2020-04-29T10:13:34.000+0200},
    address = {Wiesbaden},
    author = {Overbeck, Max},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e8306ac43dd13a2ac4511607c1d1eb71/sowi3},
    booktitle = {Das Narrativ von der Rückkehr der Religionen},
    editor = {Zapf, Holger and Hidalgo, Oliver and Hildmann, Philipp W.},
    interhash = {34f9d96413db884b58af0b8bea0aed7c},
    intrahash = {e8306ac43dd13a2ac4511607c1d1eb71},
    keywords = {MaximilianOverbeck creta eidentity sowi3},
    pages = {231-260},
    publisher = {Springer Fachmedien Wiesbaden},
    timestamp = {2020-08-04T12:16:48.000+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
    }

  • J. Pagel, N. Reiter, I. Rösiger, and S. Schulz, “A Unified Annotation Workflow for Diverse Goals,” in Proceedings of the Workshop on Annotation in Digital Humanities, co-located with ESSLLI 2018, 2018.
    [BibTeX]
    @inproceedings{Pagel2018aa,
    added-at = {2018-09-29T08:44:10.000+0200},
    author = {Pagel, Janis and Reiter, Nils and Rösiger, Ina and Schulz, Sarah},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2bf78d567fa8d6d9250c102fca42d87b0/nilsreiter},
    booktitle = {{Proceedings of the Workshop on Annotation in Digital Humanities, co-located with ESSLLI 2018}},
    editor = {Kübler, Sandra and Zinsmeister, Heike},
    interhash = {9678e5ffeaa0155241fd762e29259b7d},
    intrahash = {bf78d567fa8d6d9250c102fca42d87b0},
    keywords = {myown},
    location = {Sofia, Bulgaria},
    month = {08},
    timestamp = {2018-09-29T08:44:10.000+0200},
    title = {{A Unified Annotation Workflow for Diverse Goals}},
    year = { 2018 }
    }

  • N. Reiter and M. Willand, “Poetologischer Anspruch und dramatische Wirklichkeit: Indirekte Operationalisierung in der digitalen Dramenanalyse,” in Quantitative Ansätze in den Literatur- und Geisteswissenschaften: Systematische und historische Perspektiven, T. Bernhart, M. Willand, S. Richter, and A. Albrecht, Eds., De Gruyter, 2018, p. 45–76. doi:10.1515/9783110523300-003
    [BibTeX] [Abstract] [Download PDF]

    The influence of Shakespeare on the playwrights of Sturm und Drang is one of the most investigated areas of German drama history and its influences. However, the application of methods from computational and corpus linguistics for text content and the quantitative analysis of text structure shed a new light on this influence. In particular, we focus on formal similarities between the plays of Shakespeare and a selection of German authors between 1730 and 1804, who have explicitly expressed their relationship to Shakespeare in poetological writings. We try to compare the poetologically postulated relevance of Shakespeare to the playwrights of Sturm und Drang (and their predecessors) with the practical relevance of Shakespeare for the formal and linguistic design of their plays. Finally, the results are discussed from two perspectives, focussing on content and methods: 1. Can this analysis show Shakespeare’s influence on the design of German dramatic texts? 2. How can poetological programs be operationalized so that their realization in dramatic plays can be evaluated by digital drama analysis?

    @incollection{Reiter2018ad,
    abstract = {The influence of Shakespeare on the playwrights of Sturm und Drang is one of the most investigated areas of German drama history and its influences. However, the application of methods from computational and corpus linguistics for text content and the quantitative analysis of text structure shed a new light on this influence. In particular, we focus on formal similarities between the plays of Shakespeare and a selection of German authors between 1730 and 1804, who have explicitly expressed their relationship to Shakespeare in poetological writings. We try to compare the poetologically postulated relevance of Shakespeare to the playwrights of Sturm und Drang (and their predecessors) with the practical relevance of Shakespeare for the formal and linguistic design of their plays. Finally, the results are discussed from two perspectives, focussing on content and methods: 1. Can this analysis show Shakespeare’s influence on the design of German dramatic texts? 2. How can poetological programs be operationalized so that their realization in dramatic plays can be evaluated by digital drama analysis?},
    added-at = {2018-09-29T08:45:57.000+0200},
    author = {Reiter, Nils and Willand, Marcus},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2033e09a4b6f70f8ff788a2d2dab91cee/nilsreiter},
    booktitle = {{Quantitative Ansätze in den Literatur- und Geisteswissenschaften: Systematische und historische Perspektiven}},
    doi = {10.1515/9783110523300-003},
    editor = {Bernhart, Toni and Willand, Marcus and Richter, Sandra and Albrecht, Andrea},
    interhash = {d8ba28d4df790feac44a8efdf0a9461a},
    intrahash = {033e09a4b6f70f8ff788a2d2dab91cee},
    keywords = {myown},
    month = {04},
    pages = { 45–76 },
    publisher = { De Gruyter },
    timestamp = {2018-09-29T08:53:30.000+0200},
    title = {{Poetologischer Anspruch und dramatische Wirklichkeit: Indirekte Operationalisierung in der digitalen Dramenanalyse}},
    type = {Publication},
    url = {https://www.degruyter.com/downloadpdf/books/9783110523300/9783110523300-003/9783110523300-003.pdf},
    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 = {myown conference},
    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
    }

  • I. Rösiger, S. Schulz, and N. Reiter, “Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena,” in Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, 2018, pp. 129-138.
    [BibTeX] [Download PDF]
    @inproceedings{Roesiger2018aa,
    added-at = {2018-09-29T08:42:07.000+0200},
    author = {Rösiger, Ina and Schulz, Sarah and Reiter, Nils},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/213568e9ab91eddb10667db810b580e69/nilsreiter},
    booktitle = {{Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature}},
    interhash = {80ee06e29c1723eefe7d7c1c4e44146b},
    intrahash = {13568e9ab91eddb10667db810b580e69},
    keywords = {myown},
    location = {Santa Fe, New Mexico},
    month = {08},
    pages = { 129-138 },
    timestamp = {2018-10-30T17:50:01.000+0100},
    title = {{Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena}},
    url = {http://aclweb.org/anthology/W18-4515 },
    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 = {04},
    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 = {sentiment nlp imported myown deeplearning neural},
    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 = {08},
    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 = {08},
    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 = {04},
    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, 2017, pp. 141-147.
    [BibTeX] [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.

    @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 = {2020-03-23T21:14:46.000+0100},
    author = {Echelmeyer, Nora and Reiter, Nils and Schulz, Sarah},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23d21302e42bdfbe74e0edc3fe007573c/nora-ketschik},
    booktitle = {DHd 2017 Konferenzabstracts},
    description = {http://www.ims.uni-stuttgart.de/forschung/ressourcen/werkzeuge/PoS_Tag_MHG.html},
    interhash = {7d66653bf3ac0187f585987f534a25ac},
    intrahash = {3d21302e42bdfbe74e0edc3fe007573c},
    keywords = {myown middle-high-german POS-Tagging},
    pages = {141 - 147},
    timestamp = {2020-03-23T21:14:46.000+0100},
    title = {Ein PoS-Tagger für "das" Mittelhochdeutsche},
    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 = {imported myown dh 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 = {nlp right-wing myown extremism social mining speech hate media},
    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 = {myown visualization document visual mining, analytics, text interaction techniques, focus+context},
    timestamp = {2017-03-10T10:39:35.000+0100},
    title = {DocuCompass: Effective Exploration of Document Landscapes},
    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
    }

  • 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 = {Visualization Digital Text Humanities;},
    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 = {Humanities Digital},
    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
    }

  • 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 = {literature myown emotion dh analysis},
    month = {08},
    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 = {myown emotion caption ocr generation classification},
    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
    }

  • J. Kuhn and A. Blessing, “Die Exploration biographischer Textsammlungen mit computerlinguistischen Werkzeugen,” in Europa baut auf Biographien. Aspekte, Bausteine, Normen und Standards für eine europäische Biographik, A. Z. Bernad, C. Gruber, and M. Kaiser, Eds., Wien, Austria: new academic press, 2017, pp. 225-257.
    [BibTeX]
    @incollection{kuhnblessing2017,
    added-at = {2018-09-25T14:53:57.000+0200},
    address = { Wien, Austria },
    author = {Kuhn, Jonas and Blessing, Andre},
    biburl = {https://puma.ub.uni-stuttgart.de/bibtex/235d64f11481c19302ca1551db1741188/blessing},
    booktitle = { Europa baut auf Biographien. Aspekte, Bausteine, Normen und Standards für eine europäische Biographik },
    editor = {Bernad, Agoston Zeno and Gruber, Christine and Kaiser, Maximilian},
    interhash = {97dc646970034d3b19c060e7e678b0c0},
    intrahash = {35d64f11481c19302ca1551db1741188},
    keywords = {myown creta},
    month = {12},
    pages = { 225-257 },
    publisher = { new academic press },
    timestamp = {2018-11-05T11:24:45.000+0100},
    title = {Die Exploration biographischer Textsammlungen mit computerlinguistischen Werkzeugen},
    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 = {myown analytics visual analysis, video visualization, Movie},
    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 = {sentiment nlp imported myown emotion},
    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, 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 = {08},
    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, 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 = {myown user-interface collaboration gui digital-humanities},
    month = {09},
    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, 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 = {nlp myown digitalhumanities dh 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 = {sentiment app myown reviews},
    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, “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 = {myown digitalhumanities stemmatology pyhlogenetics Parzival},
    pages = {245-264},
    publisher = {Königshausen und Neumann},
    timestamp = {2019-09-23T11:46:25.000+0200},
    title = {Philologie und Phylogenese. Interdisziplinäre Berührungspunkte zwischen Biologie und Germanistik},
    volume = 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 = {myown digitalhumanities narratology spatialHumanities literaturwissenschaft space},
    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 = {mittelhochdeutsch myown digitalhumanities minnesang genre literaturwissenschaft},
    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 = {myown digitalhumanities narratology literaturwissenschaft 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 = {myown digitalhumanities Ovid networkAnalysis narratology spatialHumanities space},
    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
    }

  • 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 = {myown Drama Kleist Gattung Geschlecht digital-humanities},
    month = {09},
    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 = {emigration creta crosslingual},
    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 = {myown Reading, Reading Close Visualization, Digital Humanities, Text Distant},
    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 = {myown methods},
    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 = {myown Visual Reading Close Visualization, Digital Humanities, Analytics, Text Distant},
    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 = {myown methods},
    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 = {literature myown emotion analysis},
    month = {07},
    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 = {03},
    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 = {08},
    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 = {nlp imported myown social media sarcasm irony classification},
    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 = {2018-10-30T17:16:19.000+0100},
    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 = {nlp imported myown models quotations},
    month = {08},
    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 = {myown method evaluation authorship attribution},
    month = {07},
    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 = {08},
    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 = {myown PoS low-resource languages Tagging Text Historical},
    month = {05},
    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 = {sentiment app myown reviews resource corpus annotations},
    month = {05},
    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 = {11},
    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 = {cretapubs creta},
    month = {06},
    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
    }