Elamur Research
☰
home / papers / 2015 / Latent Structures for Coreference Resolution

Latent Structures for Coreference Resolution

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/Q15-1029.pdf

Summary

The paper argues that machine-learning approaches to coreference resolution differ mainly in the hidden structure they learn over, not in their basic ingredients. These approaches range from classifying individual mention pairs to ranking candidate antecedents to building document-wide antecedent trees. The authors observe that none of these structures are annotated in training corpora. They therefore cast coreference as structured prediction with latent variables. Each approach becomes a labeled directed graph over mentions, plus a dummy mention for non-anaphoric cases. Learning uses a latent structured perceptron with cost-augmented inference.

Within this single framework they implement three model families: the mention pair model, mention ranking, and antecedent trees. All three share the same preprocessing and features, so they can be compared fairly on CoNLL-2012 data. The evaluation combines scores with a qualitative error analysis. Mention ranking with latent antecedents performs best and reaches state-of-the-art results, while antecedent trees give the highest precision. The work also releases an open-source toolkit, which helps researchers design and compare coreference models systematically.

Key points

  • Published in TACL, vol. 3, pp. 405–418 (2015), by Sebastian Martschat and Michael Strube of HITS, Heidelberg.
  • Latent structures are graphs whose edges link mentions to earlier mentions. A dummy mention m0 handles non-anaphoric mentions, so anaphoricity is decided jointly with coreference. Features factor over edges, and exact decoding is done by greedy search.
  • Parameters are learned with Sun et al.'s (2009) perceptron for latent structures, combined with cost-augmented inference. This serves as a surrogate loss because entity-level metrics such as CEAFe cannot be optimized over mention pairs.
  • On CoNLL-2012, the error analysis follows Martschat and Strube (2014). Ranking beats the mention pair model because it explicitly handles anaphoricity and competition between antecedents. This yields higher precision on non-pronominal mentions and higher recall on pronouns. Latent antecedents matter mostly for very hard cases.
  • The paper sketches an extension to entity-based models via hypergraphs, with the entity-mention model as an example. The toolkit is available at smartschat.de/software.

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

41 papers of our library cite it (of the 140673 whose bibliographies we read); 9 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. DOI 10.1162/tacl_a_00147

@article{martschat2015latent,
  title = {{Latent Structures for Coreference Resolution}},
  author = {Martschat, Sebastian and Strube, Michael},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2015},
  doi = {10.1162/tacl\_a\_00147},
  url = {https://doi.org/10.1162/tacl_a_00147}
}

References

42 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mira Ariel. 1990. Accessing Noun Phrase Antecedents. Routledge, London, U.K.; New York, N.Y. find
  2. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the 1st International Conference on Language Resources and Evaluation, Granada, Spain, 28–30 May 1998, pages 563–566. find our card
  3. Eric Bengtson and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, Waikiki, Honolulu, Hawaii, 25–27 October 2008, pages 294–303. find our card
  4. Shane Bergsma and Dekang Lin. 2006. Bootstrapping path-based pronoun resolution. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, 17– 21 July 2006, pages 33–40. find
  5. Anders Björkelund and Jonas Kuhn. 2014. Learning structured perceptrons for coreference resolution with latent antecedents and non-local features. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Baltimore, Md., 22–27 June 2014, pages 47–57. find
  6. Jie Cai and Michael Strube. 2010. End-to-end coreference resolution via hypergraph partitioning. In Proceedings of the 23rd International Conference on Computational Linguistics, Beijing, China, 23–27 August 2010, pages 143–151. find
  7. Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Mark Sammons, and Dan Roth. 2012. Illinois-Coref: The UI system in the CoNLL-2012 shared task. In Proceedings of the Shared Task of the 16th Conference on Computational Natural Language Learning, Jeju Island, Korea, 12–14 July 2012, pages 113–117. find
  8. Michael Collins. 2002. Discriminative training methods for Hidden Markov Models: Theory and experiments with perceptron algorithms. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, Philadelphia, Penn., 6–7 July 2002, pages 1–8. find our card
  9. Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz, and Yoram Singer. 2006. Online passive-aggressive algorithms. Journal of Machine Learning Research, 7:551–585. find
  10. Aron Culotta, Michael Wick, and Andrew McCallum. 2007. First-order probabilistic models for coreference resolution. 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 81–88. find
  11. Pascal Denis and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, Waikiki, Honolulu, Hawaii, 25–27 October 2008, pages 660–669. find
  12. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Wash., 18–21 October 2013, pages 1971–1982. find our card
  13. Greg Durrett and Dan Klein. 2014. A joint model for entity analysis: Coreference, typing, and linking. Transactions of the Association of Computational Linguistics, 2:477–490. find
  14. Charles Elkan. 2001. The foundations of cost-sensitive learning. In Proceedings of the 17th International Joint Conference on Artificial Intelligence, Seattle, Wash., 4–10 August, 2001, pages 973–978. find
  15. Christiane Fellbaum, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, Mass. find
  16. Eraldo Fernandes, Cı́cero dos Santos, and Ruy Milidiú. 2014. Latent trees for coreference resolution. Computational Linguistics, 40(4):801–835. find
  17. Jenny Rose Finkel and Christopher Manning. 2008. Enforcing transitivity in coreference resolution. In Companion Volume to the Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, Columbus, Ohio, 15–20 June 2008, pages 45–48. find
  18. Peter Geibel and Fritz Wysotzk. 2003. Perceptron based learning with example dependent and noisy costs. In Proceedings of the 20th International Conference on Machine Learning, Washington, D.C., 21–24 August 2003, pages 218–225. find
  19. Richard W. Hamming. 1950. Error detecting and error correcting codes. Bell System Technical Journal, 26(2):147–160. find
  20. Jerry R. Hobbs. 1976. Pronoun resolution. Technical Report 76-1, Dept. of Computer Science, City College, City University of New York. find
  21. Dan Klein and Christopher D. Manning. 2001. Parsing and hypergraphs. In Proceedings of the Seventh International Workshop on Parsing Technologies (IWPT-2001), 17-19 October 2001, Beijing, China, pages 123–134. find
  22. Manfred Klenner. 2007. Enforcing consistency on coreference sets. In Proceedings of the International Conference on Recent Advances in Natural Language Processing, Borovets, Bulgaria, 27–29 September 2007, pages 323–328. find
  23. Jonathan K. Kummerfeld and Dan Klein. 2013. Error-driven analysis of challenges in coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Wash., 18–21 October 2013, pages 265–277. find our card
  24. Shalom Lappin and Herbert J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–561. find our card
  25. Heeyoung Lee, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. find our card
  26. Adam Lopez. 2009. Translation as weighted deduction. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, Athens, Greece, 30 March – 3 April 2009, pages 532–540. find
  27. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the Human Language Technology Conference and the 2005 Conference on Empirical Methods in Natural Language Processing, Vancouver, B.C., Canada, 6–8 October 2005, pages 25–32. find our card
  28. Sebastian Martschat and Michael Strube. 2014. Recall error analysis for coreference resolution. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014, pages 2070–2081. find our card
  29. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Penn., 7– 12 July 2002, pages 104–111. find our card
  30. Eric W. Noreen. 1989. Computer-Intensive Methods for Testing Hypotheses. An Introduction. Wiley, New York. find
  31. Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 Shared Task: Modeling unrestricted coreference in OntoNotes. In Proceedings of the Shared Task of the 15th Conference on Computational Natural Language Learning, Portland, Oreg., 23–24 June 2011, pages 1–27. find our card
  32. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 Shared Task: Modeling multilingual unrestricted coreference in OntoNotes. In Proceedings of the Shared Task of the 16th Conference on Computational Natural Language Learning, Jeju Island, Korea, 12–14 July 2012, pages 1–40. find our card
  33. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Baltimore, Md., 22–27 June 2014, pages 30–35. find our card
  34. Altaf Rahman and Vincent Ng. 2011. Narrowing the modeling gap: A cluster-ranking approach to coreference resolution. Journal of Artificial Intelligence Research, 40:469–521. find
  35. Emili Sapena. 2012. A constraint-based hypergraph partitioning approach to coreference resolution. Ph.D. thesis, Departament de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Spain. find
  36. Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521–544. find our card
  37. Veselin Stoyanov and Jason Eisner. 2012. Easy-first coreference resolution. In Proceedings of the 24th International Conference on Computational Linguistics, Mumbai, India, 8–15 December 2012, pages 2519– 2534. find
  38. Veselin Stoyanov, Nathan Gilbert, Claire Cardie, and Ellen Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. 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 656–664. find our card
  39. Xu Sun, Takuya Matsuzaki, Daisuke Okanohara, and Jun’ichi Tsujii. 2009. Latent variable perceptron algorithm for structured classification. In Proceedings of the 21th International Joint Conference on Artificial Intelligence, Pasadena, Cal., 14–17 July 2009, pages 1236–1242. find
  40. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Message Understanding Conference (MUC-6), pages 45–52, San Mateo, Cal. Morgan Kaufmann. find our card
  41. Xiaofeng Yang, Jian Su, Jun Lang, Chew Lim Tan, Ting Liu, and Sheng Li. 2008. An entity-mention model for coreference resolution with Inductive Logic Programming. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Columbus, Ohio, 15–20 June 2008, pages 843–851. find
  42. Chun-Nam John Yu and Thorsten Joachims. 2009. Learning structural SVMs with latent variables. In Proceedings of the 26th International Conference on Machine Learning, Montréal, Québec, Canada, 14–18 June 2009, pages 1169–1176. find