Elamur Research⌕
☰
home / papers / 2009 / Supervised Models for Coreference Resolution

Supervised Models for Coreference Resolution

Summary

This paper addresses noun phrase coreference resolution, the task of grouping mentions in a text that point to the same entity. Standard learned resolvers use mention-pair classifiers, which have two problems. They judge each candidate antecedent in isolation, without comparing it to the other candidates, and they only see features of two mentions at a time. Rahman and Ng propose a cluster-ranking model to fix both problems. For each new mention, a learned ranker scores all preceding, partially built coreference clusters and links the mention to the best one. This combines the competition between candidates that mention rankers capture with the cluster-level features of entity-mention models. The same framework can also learn discourse-new detection, meaning whether a mention starts a new entity, together with resolution. This avoids the errors that a separate pipeline detector passes on. The authors train SVM light models and test on ACE 2005, using both gold (true) and system-detected mentions. The joint cluster ranker beats mention-pair, entity-mention and mention-ranking baselines by a significant margin under MUC, CEAF and B3. The results suggest that choosing the right learning framework matters a great deal for coreference.

Key points

  • Results on true mentions: the joint cluster ranker reaches F-scores of 76.0 (MUC), 63.3 (CEAF) and 64.0 (B3). The strongest baseline, a joint mention ranker, scores 73.4, 61.6 and 62.9, and the mention-pair model scores 70.4, 54.3 and 58.0.
  • Results on system mentions: the joint cluster ranker gets MUC F = 69.3 and CEAF F = 59.5, compared with 62.5 and 53.4 for the mention-pair baseline.
  • Joint vs. pipeline: learning discourse-new detection jointly with resolution beats the pipeline setup for both rankers, mainly because precision goes up. In the pipeline setup, a separate SVM classifier with 26 features filters out discourse-new mentions first.
  • Entity-mention vs. mention-pair: the entity-mention baseline did not perform measurably better than the mention-pair model. This matches what Luo et al. (2004) found earlier.
  • Background and setup: the approach turns the heuristic, salience-based cluster scoring of Lappin and Leass (1994) into a learned model. All learners are SVM light with default parameters, and significance was tested with Approximate Randomization (p = 0.05).

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: Discourse analysis · Coreference resolution

Cited by

69 papers of our library cite it (of the 140673 whose bibliographies we read); 37 of them have a page here, 32 not yet.

Cite

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

@inproceedings{rahman2009supervised,
  title = {{Supervised Models for Coreference Resolution}},
  author = {Rahman, Altaf and Ng, Vincent},
  booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing},
  year = {2009},
  doi = {10.3115/1699571.1699639},
  url = {https://doi.org/10.3115/1699571.1699639}
}

References

40 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. A. Bagga and B. Baldwin. 1998. Entity-based cross-document coreferencing using the vector space model. In Proc. of COLING-ACL, pages 79–85. find
  2. D. Bean and E. Riloff. 1999. Corpus-based identification of non-anaphoric noun phrases. In Proc. of the ACL, pages 373–380. find our card
  3. E. Bengtson and D. Roth. 2008. Understanding the values of features for coreference resolution. In Proc. of EMNLP, pages 294–303. find
  4. S. Bergsma, D. Lin, and R. Goebel. 2008. Distributional identification of non-referential pronouns. In Proc. of ACL-08:HLT, pages 10–18. find
  5. D. Bikel, R. Schwartz, and R. Weischedel. 1999. An algorithm that learns what’s in a name. Machine Learning, 34(1–3):211–231. find
  6. D. Byron and W. Gegg-Harrison. 2004. Eliminating non-referring noun phrases from coreference resolution. In Proc. of DAARC, pages 21–26. find
  7. A. Culotta, M. Wick, and A. McCallum. 2007. First-order probabilistic models for coreference resolution. In Proc. of NAACL-HLT, pages 81–88. find our card
  8. P. Denis and J. Baldridge. 2007. Global, joint determination of anaphoricity and coreference resolution using integer programming. In Proc. of NAACL-HLT, pages 236–243. find our card
  9. P. Denis and J. Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proc. of EMNLP, pages 660–669. find our card
  10. M. Elsner and E. Charniak. 2007. A generative discourse-new model for text coherence. Technical Report CS-07-04, Brown University. find
  11. J. R. Finkel, T. Grenager, and C. Manning. 2005. Incorporating non-local information into information extraction systems by Gibbs sampling. In Proc. of the ACL, pages 363–370. find
  12. R. Florian, H. Hassan, A. Ittycheriah, H. Jing, N. Kambhatla, X. Luo, N. Nicolov, and I. Zitouni. 2004. A statistical model for multilingual entity detection and tracking. In Proc. of HLT/NAACL. find
  13. B. J. Grosz, A. K. Joshi, and S. Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–226. find our card
  14. B. J. Grosz and C. L. Sidner. 1986. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3):175–204. find our card
  15. T. Joachims. 2002. Optimizing search engines using clickthrough data. In Proc. of KDD, pages 133–142. find
  16. A. Kehler, D. Appelt, L. Taylor, and A. Simma. 2004. The (non)utility of predicate-argument frequencies for pronoun interpretation. In Proc. of HLT/NAACL. find
  17. C. Kennedy and B. Boguraev. 1996. Anaphor for everyone: Pronominal anaphora resolution without a parser. In Proc. of COLING, pages 113–118. find
  18. S. Lappin and H. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–562. find our card
  19. X. Luo, A. Ittycheriah, H. Jing, N. Kambhatla, and S. Roukos. 2004. A mention-synchronous coreference resolution algorithm based on the Bell tree. In Proc. of the ACL, pages 135–142. find our card
  20. X. Luo. 2005. On coreference resolution performance metrics. In Proc. of HLT/EMNLP, pages 25–32. find our card
  21. A. McCallum and B. Wellner. 2004. Conditional models of identity uncertainty with application to noun coreference. In Advances in NIPS. find
  22. R. Mitkov. 2002. Anaphora Resolution. Longman. find
  23. R. Mitkov. 1998. Robust pronoun resolution with limited knowledge. In Proc. of COLING/ACL, pages 869–875. find our card
  24. C. Müller. 2006. Automatic detection of nonreferential it in spoken multi-party dialog. In Proc. of EACL, pages 49–56. find
  25. V. Ng and C. Cardie. 2002a. Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution. In Proc. of COLING, pages 730–736. find
  26. V. Ng and C. Cardie. 2002b. Improving machine learning approaches to coreference resolution. In Proc. of the ACL, pages 104–111. find our card
  27. E. W. Noreen. 1989. Computer Intensive Methods for Testing Hypothesis: An Introduction. John Wiley & Sons. find
  28. M. Poesio, O. Uryupina, R. Vieira, M. Alexandrov-Kabadjov, and R. Goulart. 2004. Discourse-new detectors for definite description resolution: A survey and a preliminary proposal. In Proc. of the ACL Workshop on Reference Resolution. find
  29. S. P. Ponzetto and M. Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proc. of HLT/NAACL, pages 192–199. find our card
  30. W. M. Soon, H. T. Ng, and D. Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521–544. find our card
  31. V. Stoyanov, N. Gilbert, C. Cardie, and E. Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. In Proc. of the ACL. find our card
  32. K. Toutanova, D. Klein, C. Manning, and Y. Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In Proc. of HLT-NAACL, pages 252–259. find
  33. O. Uryupina. 2003. High-precision identification of discourse new and unique noun phrases. In Proc. of the ACL Student Research Workshop. find
  34. Y. Versley, A. Moschitti, M. Poesio, and X. Yang. 2008. Coreference systems based on kernel methods. In Proc. of COLING, pages 961–968. find
  35. R. Vieira and M. Poesio. 2000. Processing definite descriptions in corpora. In Corpus-based and Computational Approaches to Discourse Anaphora, pages 189–212. UCL Press. find
  36. M. Vilain, J. Burger, J. Aberdeen, D. Connolly, and L. Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proc. of MUC-6, pages 45–52. find our card
  37. M. Walker, A. Joshi, and E. Prince, editors. 1998. Centering Theory in Discourse. Oxford University Press. find
  38. X. Yang, G. Zhou, J. Su, and C. L. Tan. 2003. Coreference resolution using competitive learning approach. In Proc. of the ACL, pages 176–183. find
  39. X. Yang, J. Su, G. Zhou, and C. L. Tan. 2004. An NP-cluster based approach to coreference resolution. In Proc. of COLING, pages 226–232. find our card
  40. X. Yang, J. Su, J. Lang, C. L. Tan, and S. Li. 2008. An entity-mention model for coreference resolution with inductive logic programming. In Proc. of the ACL, pages 843–851. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rahman-2009-supervised-models-coreference-resolution/