T01
Transforming text across media
PI(s): Prof. Dr. Manfred Stede & Prof. Dr. Tatjana Scheffler
In collaboration with two language-technology companies, the project addresses the task of tailoring text to the conventions and requirements of different target media, in particular written blogs and microblogs (Twitter), and spoken podcasts. The focus is on the discourse-level phenomena of coreference, particle use, and coherence relations. Variation on these dimensions will be correlated with human processing ease in reading/listening experiments. The findings will then be translated into models and algorithms for identifying text passages that should be adapted, and experiments with automatically performing such adaptations will be carried out.
Members
Prof. Dr. Tatjana Scheffler
Fakultät für PhilologieGB 5/157
Hannah Seemann
Fakultät für PhilologieGB 5/156
Sara Shahmohammadi
Campus GolmHaus 14, Raum 2.13
Prof. Dr. Manfred Stede
Campus GolmHaus 14, Raum 2.31
Publications
- Peer-Reviewed: Papers, Journals, Books, Articles of the CRC
- Talk or Presentation: Talks, Presentations, Posters of the CRC
- SFB-Related: not produced in connection with the CRC, but are thematically appropriate
- Other: Papers, Journals, Books, Articles of the CRC, but not peer-reviewed
| Author(s) | Title | Year | Published in | Links | Type |
|---|---|---|---|---|---|
| Stede, M. | Automatische Textgenerierung: Ein Blick auf die Technik. | 2021 | Invited talk at the Ringvorlesung "(Un)Creative Digital Writing", Technische Universität Dresden. 25 October. | Talk or Presentation | |
| Stede, M. | Contrast in Discourse and in Argumentation. | 2021 | Invited talk at the Workshop "Integrating Perspectives on Discourse Annotation", Eberhard Karls Universität Tübingen. 04 - 05 October. | Talk or Presentation | |
| Scheffler, T., Kern, L.-A., & Seemann, H. | The medium is not the message: Individual level register variation in blogs vs. tweets. | 2022 | Register Studies, 4(2), 171-201. DOI: 10.1075/rs.22009.sch | Paper Data+Code | Peer-Reviewed |
| Seemann, H., & Scheffler, T. | Differentiating Social Media Texts via Clustering. | 2022 | Proceedings of the CHR 2022: Computational Humanities Research Conference, Antwerp, Belgium. | Paper Data+Code | Peer-Reviewed |
| Scheffler, T., Kern, L.-A., & Seemann, H. | Modal particles as markers of style, medium, and register. | 2022 | Paper presented at the Workshop: Metaphors and stance markers in register variation (MeStaR), Humboldt-Universität zu Berlin, Berlin, Germany. 16 June. | Paper | Talk or Presentation |
| Stede, M. | Computational Framing: Many Approaches - One Task? | 2023 | Invited talk at the NLP Group, Leibniz Universität Hannover, Dept. of Computer Science. Hannover, Germany. 18 May. | Talk or Presentation | |
| Shahmohammadi, S., Seemann, H., Stede, M., & Scheffler, T. | Encoding discourse structure: comparison of RST and QUD. | 2023 | n 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). Assoc. for Computational Linguistics. DOI: 10.18653/v1/2023.codi-1.11 | Data | Peer-Reviewed |
| Seemann, H., & Maršík, A. | Expressing the degree of confidence and attitude in Czech and German. | 2023 | Poster presented at the 10th International Contrastive Linguistics Conference (ICLC-10), University of Mannheim, Mannheim, Germany. 18-21 July. | Data+Code | Peer-Reviewed |
| Scheffler, T. | Individual linguistic variability in social media. | 2023 | Invited talk at the CMC 2023: CMC-CORPORA 2023, University of Mannheim, Mannhein, Germany. 14 September. | Talk or Presentation | |
| Seemann, H., Shahmohammadi, S., Scheffler, T., & Stede, M. | Building a Parallel Discourse-Annotated Multimedia Corpus. | 2023 | Poster presented at the CMC 2023: CMC-CORPORA 2023, University of Mannheim, Mannheim, Germany. 14-15 September. | Data | Talk or Presentation |
