SFB 1287 Sonderforschungsbereich 1287 Die Grenzen der Variabilität in der Sprache: Kognitive, komputationale und grammatische Aspekte

Projekt T01

in Phase 2

Texttransformation in verschiedenen Medien

PI(s): Prof. Dr. Manfred Stede & Prof. Dr. Tatjana Scheffler

In Zusammenarbeit mit zwei Sprachtechnologie-Unternehmen untersucht das Projekt die Aufgabe der Adaption von Texten an die Konventionen und Erfordernisse verschiedener Medien, insbesondere geschriebene Blogs und Microblogs (Twitter) sowie gesprochene Podcasts. Im Zentrum der Arbeit stehen Phänomene der Diskursebene, nämlich Koreferenz, Partikelgebrauch und Kohärenzrelationen. Variation entlang dieser Dimensionen wird in Lese/Hör-Experimenten im Hinblick auf Verarbeitungsgeschwindigkeit getestet, und die gewonnenen Erkenntnisse werden schließlich in Modelle und Algorithmen übersetzt, die adaptionswürdige Textpassagen identifizieren und auch mit der automatischen Umsetzung solcher Adaptionsschritte experimentieren.

Papers

AutorenTitelJahrErschienen inLinks
Scheffler, T., Kern, L.-A., & Seemann, H. J.The medium is not the message: Individual level register variation in blogs vs. tweets.2022Register Studies, 4(2), 171-201.
Seemann, H. J., & Scheffler, T.Differentiating Social Media Texts via Clustering.2022In F. Karsdorp, A. Lassche, & K. Nielbo (Eds.), Proceedings of the Computational Humanities Research Conference 2022 (pp. 177-188). Antwerp, Belgium.
Shahmohammadi, S., Seemann, H. J., Stede, M., & Scheffler, T.Encoding discourse structure: comparison of RST and QUD.2023In M. Strube, C. Braud, C. Hardmeier, J. J. Li, S. Loáiciga, & A. Zeldes (Eds.), Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), (pp. 89–98), Toronto, Canada. Association for Computational Linguistics. *
Shahmohammadi, S., & Stede, M.Discourse Parsing for German with new RST Corpora.2024Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024), pp. 65-74. Vienna, Austria: Association for Computational Linguistics.
Seemann, H. J., Shahmohammadi, S., Stede, M., & Scheffler, T.Spoken vs. Written Computer-Mediated Communiation.2024Proceedings of the 11th Conference on CMC and Social Media Corpora for the Humanities (CMC 2024), pp. 70-74. Université Côte d'Azur, Nice, France.
Seemann, H. J., Shahmohammadi, S., Stede, M., & Scheffler, T.Discourse-Level Features in Spoken and Written Communication.2024Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024), pp. 292–302. Vienna, Austria: Association for Computational Linguistics.
Seemann, H.Modalpartikel2024In D. Gutzmann, K. Turgay, & T. E. Zimmermann (Eds.), Semantik und Pragmatik. Wörterbücher zur Sprach- und Kommunikationswissenschaft (WSK) Online. Berlin: De Gruyter.
Seemann, H., & Scheffler, T.German Modal Particles as Discourse Signals.2025Dialogue & Discourse, 16(1), 1-30.
Scheffler, T., & Seemann, H.Review: Remus Gergel, Ingo Reich & Augustin Speyer (eds.)(2022): Particles in German, English, and Beyond. Amsterdam/Phil- adelphia: John Benjamins.2025Linguistische Berichte, 281, 111-118.
Scheffler, T.Social media corpora for analyzing linguistic variation.2025In L. Cotgrove, L. Herzberg, & H. Lüngen (Eds.), Exploring digitally-mediated communication with corpora: Methods, analyses, and corpus construction (pp. 329-348). De Gruyter.
Hewett, F., & Stede, M.Disagreements in analyses of rhetorical text structure: A new dataset and first analyses.2025In S. Peng & I. Rehbein (Eds.), Proceedings of the 19th Linguistic Annotation Workshop (LAW-XIX-2025) (pp. 35–47). Association for Computational Linguistics.

Talks

AutorenTitelJahrErschienen inLinks
Scheffler, T., Kern, L.-A., & Seemann, H. J.Modal particles as markers of style, medium, and register.2022Paper presented at the Workshop: Metaphors and stance markers in register variation (MeStaR), Humboldt-Universität zu Berlin, Berlin, Germany. 16 June.
Stede, M.Computational Framing: Many Approaches - One Task?2023Invited talk at the NLP Group, Leibniz Universität Hannover, Dept. of Computer Science. Hannover, Germany. 18 May.
Scheffler, T.Individual linguistic variability in social media.2023Invited talk at the CMC 2023: CMC-CORPORA 2023, University of Mannheim, Mannhein, Germany. 14 September.
Seemann, H. J., Shahmohammadi, S., Scheffler, T., & Stede, M.Building a Parallel Discourse-Annotated Multimedia Corpus.2023Poster presented at the CMC 2023: CMC-CORPORA 2023, University of Mannheim, Mannheim, Germany. 14-15 September.
Seemann, H. J., & Maršík, A.Expressing the degree of confidence and attitude in Czech and German.2023Poster presented at the 10th International Contrastive Linguistics Conference (ICLC-10), University of Mannheim, Mannheim, Germany. 18-21 July.
Seemann, H. J.Modal Particles as Markers in Discourse.2024Paper presented at the Conference on Discourse Markers: Markers in Discourse and Markers on Discourse. Metz, France. 21 - 22 June.
Kontakt
Universität Potsdam
Department Linguistik
Prof. Dr. Doreen Georgi
Karl-Liebknecht-Strasse 24-25
Haus 14, Raum 3.33
14476 Potsdam

(+49) 331 977-2968
doreen.georgi@uni-potsdam.de
Anfahrt