Mova0.5 pre-release⌕
☰
home / docs / papers / English / Variation in Coreference Strategies across Genres and Production Media

Variation in Coreference Strategies across Genres and Production Media

What it is about

A corpus study of how referring expressions and coreference chains differ across genres and media: the English OntoNotes sections (telephone and broadcast conversation, broadcast news, newswire, web blogs), Switchboard, and a corpus of Twitter conversation threads, after harmonising tokenisation, pronoun forms and NP spans. Measures are frequency (pronouns vs full NPs, pronoun person), NP heaviness (length and tree height), and distance between a third-person pronoun and its antecedent in tokens, clauses and NPs, with and without discourse markers and parenthetical clauses. Spontaneous speech (Switchboard, telephone) and edited writing (newswire, blogs) form two clear groups: speech has far more pronouns (especially first and second person), lighter NPs, and more fillers and parentheticals; Twitter and broadcast conversation fall between, differently for each measure. Token distance does not separate genres reliably; clause- and NP-based distances do.

Ideas

For Mova

35. Reference and coreference §2 (salience), §8–9; 37-register-and-variation.md §3 (spoken and written English). Code: coref/src/sieve.rs (window), coref/src/eval.rs (genre profile). Measures: per-pronoun precision and CoNLL F1 on GUM dev; profile distances between Mova texts and GUM genres.

Topics: Discourse analysis · Coreference resolution

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.508

@inproceedings{aktas2020variation,
  title = {{Variation in Coreference Strategies across Genres and Production Media}},
  author = {Aktaş, Berfin and Stede, Manfred},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.508},
  url = {https://doi.org/10.18653/v1/2020.coling-main.508}
}

References

33 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Berfin Aktaş, Tatjana Scheffler, and Manfred Stede. 2018. Anaphora Resolution for Twitter Conversations: An Exploratory Study. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 1–10, New Orleans, Louisiana, June. Association for Computational Linguistics. find
  2. Berfin Aktaş, Tatjana Scheffler, and Manfred Stede. 2019. Coreference in English OntoNotes: Properties and Genre Differences. In Kamil Ekštein, editor, Text, Speech, and Dialogue, pages 171–184, Cham. Springer International Publishing. find
  3. Berfin Aktaş, Veronika Solopova, Annalena Kohnert, and Manfred Stede. 2020. Adapting Coreference Resolution to Twitter Conversations. In Findings of EMNLP. Association for Computational Linguistics. find
  4. Marilisa Amoia, Kerstin Kunz, and Ekaterina Lapshinova-Koltunski. 2012. Coreference in Spoken vs. Written Texts: a Corpus-based Analysis. In Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey, May. European Language Resources Association (ELRA). find
  5. BBN Technologies, 2007. Co-reference Guidelines for English OntoNotes Version 7.0. find
  6. Douglas Biber, Edward Finegan, Stig Johansson, Susan Conrad, and Geoffrey Leech. 1999. Longman Grammar of Spoken and Written English. Longman. find
  7. Douglas Biber. 1992. Using computer-based text corpora to analyze the referential strategies of spoken and written texts. In Jan Svartvik, editor, Directions in Corpus Linguistics: Proceedings of Nobel Symposium 82, Stockholm, 4-8 August 1991, pages 213–252. Berlin:Mouton. find
  8. Donna K. Byron. 2002. Resolving pronominal reference to abstract entities. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 80–87, Philadelphia, Pennsylvania, USA, July. Association for Computational Linguistics. find
  9. Sasha Calhoun, Jean Carletta, Jason M. Brenier, Neil Mayo, Dan Jurafsky, Mark Steedman, and David Beaver. 2010. The NXT-format Switchboard Corpus: A rich resource for investigating the syntax, semantics, pragmatics and prosody of dialogue. Language Resources and Evaluation, 44(4):387–419, 12. find
  10. Wallace L. Chafe. 1982. Integration and involvement in speaking, writing, and oral literature. In Deborah Tannen, editor, Spoken and Written Language: Exploring Orality and Literacy, pages 35–53. Norwood, NJ: Ablex. find
  11. Miriam Eckert and Michael Strube. 2000. Dialogue Acts, Synchronizing Units, and Anaphora Resolution. Journal of Semantics, 17(1):51–89. find our card
  12. S. Engell. 2016. Coreference in English and German: A Theoretical Framework and Its Application in a Study of Court Decisions. Logos Verlag Berlin. find
  13. Barbara A. Fox. 1987. Discourse structure and anaphora : written and conversational English / Barbara A. Fox. Cambridge University Press Cambridge [Cambridgeshire] ; New York. find
  14. J. Godfrey, E. Holliman, and J. McDaniel. 1992. SWITCHBOARD: telephone speech corpus for research and development. In IEEE International Conference on Speech, and Signal Processing, ICASSP-92, volume 1, pages 517–520. find
  15. Christian Hardmeier, Luca Bevacqua, Sharid Loáiciga, and Hannah Rohde. 2018. Forms of Anaphoric Reference to Organisational Named Entities: Hoping to widen appeal, they diversified. In Proceedings of the Seventh Named Entities Workshop, pages 36–40, Melbourne, Australia, July. Association for Computational Linguistics. find
  16. Ewa Jonsson. 2016. Conversational Writing: A Multidimensional Study of Synchronous and Supersynchronous Computer-mediated Communication. English Corpus Linguistics. Peter Lang, Frankfurt am Main. find
  17. Peter Koch and Wulf Oesterreicher. 1985. Sprache der Nähe - Sprache der Distanz. Müdlichkeit und Schriftlichkeit im Spannungsfeld von Sprachtheorie und Sprachgeschichte. Romanistisches Jahrbuch, 36(1985):15 – 43. find
  18. Kerstin Kunz and Ekaterina Lapshinova-Koltunski. 2015. Cross-linguistic analysis of discourse variation across registers. Cross-linguistic Studies at the Interface between Lexis and Grammar. Nordic Journal of English Studies., 14:258–288. find
  19. Kerstin Kunz, Ekaterina Lapshinova-Koltunski, and José Manuel Martı́nez. 2016. Beyond identity coreference: Contrasting indicators of textual coherence in English and German. In Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016), pages 23–31, San Diego, California, June. Association for Computational Linguistics. find our card
  20. Ekaterina Lapshinova-Koltunski. 2015. Exploration of inter- and intralingual variation of discourse phenomena. In Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT@EMNLP), pages 158– 167, Lisbon, Portugal, September. Association for Computational Linguistics. find
  21. Christian Mair. 2006. Twentieth-Century English: History, Variation and Standardization. Studies in English Language. Cambridge University Press. find
  22. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60, Baltimore, Maryland, June. Association for Computational Linguistics. find
  23. Stella Neumann and Jennifer Fest. 2016. Cohesive devices across registers and varieties: The role of medium in English. In Variational text linguistics : revisiting register in English / edited by Christoph Schubert, Christina Sanchez-Stockhammer, volume 90 of Topics in English Linguistics, pages 195–220. De Gruyter, Berlin, Boston. find
  24. Sameer Pradhan, Lance Ramshaw, Ralph Weischedel, Jessica Macbride, and Linnea Micciulla. 2007. Unrestricted Coreference: Identifying Entities and Events in OntoNotes. International Conference on Semantic Computing, 0:446–453, 09. find
  25. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards Robust Linguistic Analysis using OntoNotes. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143–152. Association for Computational Linguistics. find
  26. Thomas Proisl and Peter Uhrig. 2016. SoMaJo: State-of-the-art tokenization for German web and social media texts. In Proceedings of the 10th Web as Corpus Workshop, pages 57–62, Berlin, August. Association for Computational Linguistics. find
  27. Catherine Schnedecker. 2018. Reference chains and genre identification: From Discrete to Non-Discrete Units. In Thierry Charnois Dominique Legallois and Meri Larjavaara, editors, The Grammar of Genres and Styles, page 39–66. De Gruyter Mouton. find
  28. Michael Strube and Christoph Müller. 2003. A machine learning approach to pronoun resolution in spoken dialogue. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 168–175, Sapporo, Japan, July. Association for Computational Linguistics. find
  29. Ann Taylor, Mitchell Marcus, and Beatrice Santorini. 2003. The Penn Treebank: An Overview. In Abeillé A., editor, Treebanks, volume 20 of Text, Speech and Language Technology. Springer, Dordrecht. find
  30. Olga Uryupina and Massimo Poesio. 2012. Domain-specific vs. Uniform Modeling for Coreference Resolution. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012), pages 187–191, Istanbul, Turkey, May. European Language Resources Association (ELRA). find
  31. Thomas Wasow and Jennifer Arnold, 2011. Post-verbal constituent ordering in English, pages 119–154. De Gruyter Mouton, 01. find
  32. Thomas Wasow. 1997. Remarks on grammatical weight. Language Variation and Change, 9:81 – 105, 03. find
  33. Amir Zeldes. 2018. A Predictive Model for Notional Anaphora in English. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 34–43, New Orleans, Louisiana, June. Association for Computational Linguistics. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/akta-2020-variation-coreference-strategies-across-genres/