Project A03 (finished)
Discourse Strategies across Social Media: Variability in Individuals, Groups, and Channels
PI(s): Prof. Dr. Tatjana Scheffler & Prof. Dr. Manfred Stede
Language in social media is characterised by more formal (written-like) or more informal (spoken-like) style in different contexts, and thus shows high variability. In this project, we focus on one linguistic domain in pragmatics, the management of common ground between writers and readers, and identify the consistent patterns of discourse strategies employed by writers across different groups and channels. We explore three types of phenomena that relate to common ground management: question tags, coreferential expressions, and coherence markers.
Question tags are particles attaching to a typically declarative clause to yield a kind of confirmation request. We conducted an extensive corpus study investigating the contexts and functions of different question tag variants in German. We found significant differences between the functions of individual tags and in the use of tags across conversational corpora (Twitter and spoken corpora), showing that only some uses of tags carry over from speech to written conversation. We are currently working on both computational and formal linguistic models that capture this variability.
Regarding coreferential relations, the research literature yielded partly conflicting results, but it is generally accepted that their behavior differs between spoken and written language, for example in the length of referential chains, and the type of expression (pronoun or full noun phrase, for example) that is used. We extended this research to include social media conversations from Twitter, showing that coreferential relations on Twitter are more similar to spoken data than written. In the following, we have adapted a computational model for automatic coreference resolution to better capture the idiosyncrasies of social media conversations.
Finally, we are investigating the realization of coherence relations in different social media. In existing corpus research, it is often unclear if differences between corpora are due to confounds such as the topic of discourse, the authors/speakers included in the corpus, the language, the time of recording, etc. We address this by studying texts from two social media (Twitter and blogs) from the same authors and on similar topics. This allows us to pinpoint the effect of individual medium constraints such as the mode (spoken vs. written) or the text type (narrative vs. interactive) from individual stylistic variation and topic effects, and identify what stays stable wrt. coherence relation marking across all these dimensions.
Papers
| Author(s) | Title | Year | Published in | Links |
|---|---|---|---|---|
| Aktaş, B., Scheffler, T., & Stede, M. | Anaphora Resolution for Twitter Conversations: An Exploratory Study. | 2018 | In M. Poesio, V. Ng, & M. Ogrodniczuk (Eds.), Proceedings of the First Workshop on Computational Models of Reference, Anaphora, and Coreference (pp. 1-10). New Orleans: Association for Computational Linguistics. * DOI: 10.18653/v1/W18-0701 | |
| Das, D., Scheffler, T., Bourgonje, P., & Stede, M. | Constructing a Lexicon of English Discourse Connectives. | 2018 | In K. Komtani, D. Litman, K. Yu, A. Papangelis, L. Cavedon, & M. Nakano (Eds.), Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pp. 360-365. * | |
| Stede, M., Scheffler, T., & Mendes, A. | Connective-Lex: A Web-Based Multilingual Lexical Resource for Connectives. | 2019 | Discours. Revue de linguistique, psycholinguistique et informatique, 24, 3-38 DOI: 10.4000/discours.10098 | |
| Aktaş, B., Scheffler, T., & Stede, M. | Coreference in English OntoNotes: Properties and Genre Differences. | 2019 | In K. Ekštein (Ed.), Text, Speech, and Dialogue: Proceedings of the 22nd International Conference on Text, Speech and Dialogue (TSD 2019) (pp. 171-184): Springer International Publishing. * DOI: 10.1007/978-3-030-27947-9_15 | |
| Clausen, Y., & Nastase, V. | Metaphors in Text Simplification: To change or not to change, that is the question. | 2019 | In H. Yannakoudakis, E. Kochmar, C. Leacock, N. Madnani, I. Pilán, & T. Zesch (Eds.), Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications (pp. 423–434). Florence: Association for Computational Linguistics. * | |
| Scheffler, T., Aktaş, B., Das, D., & Stede, M. | Annotating Shallow Discourse Relations in Twitter Conversations. | 2019 | In A. Zeldes, D. Das, E. M. Galani, J. D. Antonio, & M. Iruskieta (Eds.), Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019 (pp. 50-55). Minneapolis, MN.: Association for Computational Linguistics. * | |
| Aktaş, B., & Stede, M. | Variation in Coreference Strategies across Genres and Production Media. | 2020 | In D. Scott, N. Bel, & C. Zong (Eds.), Proceedings of the 28th International Conference on Computational Linguistics (COLING) (pp. 5774-5785). Barcelona, Spain: International Committee on Computational Linguistics. * | |
| Aktaş, B., & Kohnert, A. | TwiConv: A Coreference-annotated Corpus of Twitter Conversations. | 2020 | In M. Ogrodniczuk, V. Ng, Y. Grishina, & S. Pradhan (Eds.), Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC@COLING) (pp. 47-54). Barcelona, Spain: Association for Computational Linguistics. * | |
| Aktaş, B., Solopova, V., Kohnert, A., & Stede, M. | Adapting Coreference Resolution to Twitter Conversations. | 2020 | T. Cohn, Y. He, & Y. Liu (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2020 (pp. 2454-2460): Association for Computational Linguistics. * | |
| Bevacqua, L., & Scheffler, T. | Form Variation of Pronominal It-Clefts in Written English. | 2020 | Linguistic Vanguard, 6(1), 20190066. DOI: 10.1515/lingvan-2019-0066 | |
| Clausen, Y., & Scheffler, T. | Commitments in German Tag Questions: An Experimental Study. | 2020 | In S. Malamud, J. Pustejovski, & J. Ginzburg (eds.), Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers (SEMDIAL). * | |
| Clausen, Y., & Scheffler, T. | A corpus-based analysis of meaning variations in German tag questions. Evidence from spoken and written conversational corpora. | 2022 | Corpus Linguistics and Linguistic Theory, 18(1), 1-31. DOI: 10.1515/cllt-2019-0060 | |
| Aktaş, B., & Stede, M. | Anaphoric Distance in Oral and Written Language: Experimental Evidence. | 2022 | Discours. Revue de linguistique, psycholinguistique et informatique, 31, 1-35. DOI: 10.4000/discours.12383 | |
| Aktaş, B., Clausen, Y., Scheffler, T., & Stede, M. | Diskursstrategien in Sozialen Medien. | 2020 | K. Marx, H. Lobin, & A. Schmidt (Eds.), Deutsch in Sozialen Medien. Interaktiv - multimodal - vielfältig (pp. 369–372). Boston, Berlin: de Gruyter. | |
| Clausen, Y. | You shall know a tag by the context it occurs in: An analysis of German tag questions and their responses in spontaneous conversations. | 2021 | In A. Holtz, I. Kovač, R. Puggaard-Rode, & J. Wall (Eds.), ConSOLE XXIX: Proceedings of the 29th Conference of the Student Organization of Linguistics in Europe (pp. 116-140). Leiden: Leiden University Centre for Linguistics. * | |
| Aktaş, B. | Variation in coreference patterns. | 2023 | PhD Thesis. Potsdam: Universitätsverlag Potsdam. DOI: 10.25932/publishup-59608 | |
| Clausen, Y., & Stede, M. | Discourse connectives and their arguments: an experiment on anaphoricity in German. | 2022 | Linguistics Vanguard, 8(1), 95-111. DOI: 10.1515/lingvan-2021-0102 |
