Elamur Research
☰
home / papers / 2012 / Collective Classification for Fine-grained Information Status

Collective Classification for Fine-grained Information Status

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/P12-1084.pdf

Summary

The paper addresses automatic recognition of information status (IS) for noun-phrase mentions: whether a referent is old, new, or mediated, meaning inferable from context or world knowledge. Earlier systems worked only on Switchboard dialogue and used three coarse classes. The authors move the task to written news and split mediated mentions into six subtypes, including comparative and bridging anaphora. They added an IS layer to 50 Wall Street Journal texts from OntoNotes, about 11k mentions, and confirmed with a three-annotator study that the scheme is reliable. Their main claim is that a mention's IS also depends on nearby mentions, so they label all mentions jointly. They combine new linguistic features with relational links between mentions, of which syntactic parent–child structure proved useful. Compared with reimplementations of Nissim (2006) and Rahman and Ng (2011), the method raises coarse accuracy by roughly 10 and 5 points. Most of this gain comes from better separation of new and mediated mentions. Bridging remains very difficult to detect, which questions prior work's focus on antecedent selection alone.

Key points

  • The corpus contains 50 WSJ texts from OntoNotes with 10,980 gold mentions. It covers coreference, bridging and comparative antecedents and was planned as a public OntoNotes annotation layer.
  • Cohen's κ across annotator pairs was about 75–77 on the coarse level and 77–80 on the fine level (9 categories). Bridging had the lowest agreement, at roughly 61–71.
  • The collective "hasChild" relation significantly improved over local classification, mainly for mediated/synt and mediated/aggregate. A word-order "precedes" relation gave no further improvement.
  • Results for the Rahman and Ng-based setup:
    • Coarse accuracy rose from 74.9 (original local classifier) to 79.8 (RahmanNg+ol+hasChild).
    • Fine-grained accuracy rose from 72.6 to 77.5.
  • The simple decision-tree variant Nissim+ol+hasChild matched the feature-heavy Rahman and Ng variant. Comparatives were recognized reliably, while bridging (about 6% of mentions) stayed at very low F-scores.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

53 papers of our library cite it (of the 140673 whose bibliographies we read); 13 of them have a page here, 40 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{markert2012collective,
  title = {{Collective Classification for Fine-grained Information Status}},
  author = {Markert, Katja and Hou, Yufang and Strube, Michael},
  booktitle = {Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2012},
  url = {https://aclanthology.org/P12-1084/}
}

References

39 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ron Artstein and Massimo Poesio. 2008. Inter-coder agreement for computational linguistics. Computational Linguistics, 34(4):555–596. find
  2. Regina Barzilay and Mirella Lapata. 2008. Modeling local coherence: An entity-based approach. Computational Linguistics, 34(1):1–34. find our card
  3. Betty J. Birner and Gregory Ward. 1998. Information Status and Noncanonical Word Order in English. John Benjamins, Amsterdam, The Netherlands. find
  4. Aoife Cahill and Arndt Riester. 2009. Incorporating information status into generation ranking. In Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing, Singapore, 2–7 August 2009, pages 817–825. find our card
  5. Jie Cai, Éva Mújdricza-Maydt, and Michael Strube. 2011. Unrestricted coreference resolution via global hypergraph partitioning. In Proceedings of the Shared Task of the 15th Conference on Computational Natural Language Learning, Portland, Oreg., 23–24 June 2011, pages 56–60. find
  6. Jean Carletta. 1996. Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22(2):249–254. find our card
  7. Michael Collins and Nigel Duffy. 2001. Convolution kernels for natural language. In Advances in Neural Information Processing Systems 14, Vancouver, B.C., Canada, 3–8 December, 2001, pages 625–632, Cambridge, Mass. MIT Press. find
  8. Pascal Denis and Jason Baldridge. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In Proceedings of Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Rochester, N.Y., 22–27 April 2007, pages 236–243. find
  9. Katja Filippova and Michael Strube. 2007. Generating constituent order in German clauses. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, Prague, Czech Republic, 23–30 June 2007, pages 320–327. find
  10. Claire Gardent and Hélène Manuélian. 2005. Création d’un corpus annoté pour le traitement des descriptions définies. Traitement Automatique des Langues, 46(1):115–140. find
  11. Barbara J. Grosz, Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–225. Iorn Korzen and Matthias Buch-Kromann. Anaphoric relations in the Copenhagen dependency treebanks. In S. Dipper and H. Zinsmeister, editors, Corpus-based Investigations of Pragmatic and Discourse Phenomena, volume 3 of Bochumer Linguistische Arbeitsberichte, pages 83–98. University of Bochum, Bochum, Germany. find our card
  12. Ivana Kruijff-Korbayová and Mark Steedman. 2003. Discourse and information structure. Journal of Logic, Language and Information. Special Issue on Discource and Information Structure, 12(3):149–259. find
  13. Knud Lambrecht. 1994. Information Structure and Sentence Form. Cambridge, U.K.: Cambridge University Press. find
  14. Qing Lu and Lise Getoor. 2003. Link-based classification. In Proceedings of the 20th International Conference on Machine Learning, Washington, D.C., 21–24 August 2003, pages 496–503. find
  15. Sofus A. Macskassy and Foster Provost. 2007. Classification in networked data: A toolkit and a univariate case study. Journal of Machine Learning Research, 8:935–983. find
  16. Katja Markert and Malvina Nissim. 2005. Comparing knowledge sources for nominal anaphora resolution. Computational Linguistics, 31(3):367–401. find
  17. Josef Meyer and Robert Dale. 2002. Mining a corpus to support associative anaphora resolution. In Proceedings of the 4th International Conference on Discourse Anaphora and Anaphor Resolution, Lisbon, Portugal, 18–20 September, 2002. find
  18. Natalia M. Modjeska, Katja Markert, and Malvina Nissim. 2003. Using the web in machine learning for other-anaphora resolution. In Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, Sapporo, Japan, 11–12 July 2003, pages 176–183. find
  19. Ani Nenkova, Jason Brenier, Anubha Kothari, Sasha Calhoun, Laura Whitton, David Beaver, and Dan Jurafsky. 2007. To memorize or to predict: Prominence labeling in conversational speech. In Proceedings of Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Rochester, N.Y., 22–27 April 2007, pages 9–16. find
  20. Vincent Ng. 2009. Graph-cut-based anaphoricity determination for coreference resolution. In Proceedings of Human Language Technologies 2009: The Conference of the North American Chapter of the Association for Computational Linguistics, Boulder, Col., 31 May – 5 June 2009, pages 575–583. find
  21. Malvina Nissim, Shipara Dingare, Jean Carletta, and Mark Steedman. 2004. An annotation scheme for information status in dialogue. In Proceedings of the 4th International Conference on Language Resources and 2011. Evaluation, Lisbon, Portugal, 26–28 May 2004, pages 1023–1026. find
  22. Malvina Nissim. 2006. Learning information status of discourse entities. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, Sydney, Australia, 22–23 July 2006, pages 94–012. find
  23. Bo Pang and Lillian Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, 21–26 July 2004, pages 272–279. find
  24. Massimo Poesio, Rahul Mehta, Axel Maroudas, and Janet Hitzeman. 2004. Learning to resolve bridging references. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, 21–26 July 2004, pages 143–150. find
  25. Massimo Poesio. 2004. The MATE/GNOME proposals for anaphoric annotation, revisited. In Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue, Cambridge, Mass., 30 April – 1 May 2004, pages 154– 162. find
  26. Scott Prevost. 1996. An information structural approach to spoken language generation. In Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics, Santa Cruz, Cal., 24–27 June 1996, pages 294–301. find
  27. Ellen F. Prince. 1981. Towards a taxonomy of given-new information. In P. Cole, editor, Radical Pragmatics, pages 223–255. Academic Press, New York, N.Y. find
  28. Ellen F. Prince. 1992. The ZPG letter: Subjects, definiteness, and information-status. In W.C. Mann and S.A. Thompson, editors, Discourse Description. Diverse Linguistic Analyses of a Fund-Raising Text, pages 295–325. John Benjamins, Amsterdam. find
  29. Altaf Rahman and Vincent Ng. 2011. Learning the information status of noun phrases in spoken dialogues. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Scotland, U.K., 27–29 July 2011, pages 1069–1080. find
  30. Arndt Riester, David Lorenz, and Nina Seemann. 2010. A recursive annotation scheme for referential information status. In Proceedings of the 7th International Conference on Language Resources and Evaluation, La Valetta, Malta, 17–23 May 2010, pages 717–722. find
  31. Julia Ritz, Stefanie Dipper, and Michael Götze. 2008. Annotation of information structure: An evaluation across different types of texts. In Proceedings of the 6th International Conference on Language Resources and Evaluation, Marrakech, Morocco, 26 May – 1 June 2008, pages 2137–2142. find
  32. Ryohei Sasano and Sadao Kurohashi. 2009. A probabilistic model for associative anaphora resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore, 6–7 August 2009, pages 1455–1464. find
  33. Advaith Siddharthan, Ani Nenkova, and Kathleen McKeown. 2011. Information status distinctions and referring expressions: An empirical study of references to people in news summaries. Computational Linguistics, 37(4):811–842. find
  34. Swapna Somasundaran, Galileo Namata, Janyce Wiebe, and Lise Getoor. 2009. Supervised and unsupervised methods in employing discourse relations for improving opinion polarity classification. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore, 6–7 August 2009. find
  35. Ben Taskar, Pieter Abbeel, and Daphne Koller. 2002. Discriminative probabilistic models for relational data. In Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence, Edmonton, Alberta, Canada, 1-4 August 2002, pages 485–492. find
  36. Renata Vieira and Massimo Poesio. 2000. An empirically-based system for processing definite descriptions. Computational Linguistics, 26(4):539– 593. find
  37. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, and Ann Houston. 2011. OntoNotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium. find
  38. Yiming Yang, Seán Slattery, and Rayid Ghani. 2002. A study of approaches to hypertext categorization. Journal of Intelligent Information Systems, 18(2-3):219– 241. find
  39. Guodong Zhou and Fang Kong. 2009. Global learning of noun phrase anaphoricity in coreference resolution via label propagation. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore, 6–7 August 2009, pages 978–986. find