Elamur Research⌕
☰
home / papers / 2014 / Latent Trees for Coreference Resolution

Latent Trees for Coreference Resolution

Summary

The paper addresses unrestricted coreference resolution: finding which mentions in a document point to the same entity, and keeping only the clusters with more than one mention. The authors treat the mentions of a document as nodes in a graph, with directed arcs between candidate coreferent pairs. Clustering then becomes the task of finding a set of trees in this graph. Because the gold trees are not annotated, they are treated as hidden structures. A large-margin latent structured perceptron learns them, and the Chu-Liu-Edmonds optimal branching algorithm decodes them. Entropy-guided feature induction automatically combines basic arc features into richer conjunctions, which lets a linear learner behave like a nonlinear model. The same system runs on the Arabic, Chinese and English CoNLL-2012 Shared Task data, with only small language-specific changes such as pronoun lists. It won the closed track. A later version adds nested-mention candidate arcs for Chinese and reaches the best reported results for all three languages. The work shows that latent trees keep structured coreference learning tractable without sacrificing accuracy.

Key points

  • Pipeline: rule-based mention detection (adapted from dos Santos and Carvalho 2011) → candidate arcs from sieves (adapted from Lee et al. 2013) → basic and EFI-induced features → latent tree learning and prediction → clusters read directly from the trees. Verbs are not used as mentions, so event coreference is not handled.
  • Metric: the CoNLL-2012 score, i.e. the unweighted average of MUC, B³ and CEAF_e, further averaged over the three languages.
  • Shared Task results: the submitted system scored 54.22 (Arabic), 58.49 (Chinese) and 63.37 (English), for an official score of 58.69, the best among participants.
  • Improved version: adding nested-mention arcs for Chinese raises that language's score by almost 4.5 points. The overall score rises to 60.15 (+1.46 absolute, a 3.5% error reduction).
  • Error analysis: wrongly attaching a singleton to a tree accounts for 45% of errors in Arabic, 37.7% in Chinese and 31.9% in English. Pleonastic "it" is a notable source of these errors in English. The authors propose higher-order and cluster-sensitive features as future work.

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

18 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 13 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00200

@article{fernandes2014latent,
  title = {{Latent Trees for Coreference Resolution}},
  author = {Fernandes, Eraldo Rezende and Santos, Cícero Nogueira dos and Milidiú, Ruy Luiz},
  journal = {Computational Linguistics},
  year = {2014},
  doi = {10.1162/coli\_a\_00200},
  url = {https://doi.org/10.1162/coli_a_00200}
}

References

66 references, 44 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bagga, Amit and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference, pages 563–566, Granada. find our card
  2. Bansal, Mohit and Dan Klein. 2012. Coreference semantics from web Features. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 389–398, Jeju Island. find our card
  3. Bengtson, Eric and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 294–303, Honolulu, HI. find our card
  4. Bergsma, Shane and Dekang Lin. 2006. Bootstrapping path-based pronoun resolution. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 33–40, Sydney. find our card
  5. Björkelund, Anders and Richárd Farkas. 2012. Data-driven multilingual coreference resolution using resolver stacking. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 49–55, Jeju Island. find our card
  6. Björkelund, Anders and Pierre Nugues. 2011. Exploring lexicalized features for coreference resolution. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 45–50, Portland, OR. find
  7. Cai, Jie, Eva Mujdricza-Maydt, and Michael Strube. 2011. Unrestricted coreference resolution via global hypergraph partitioning. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 56–60, Portland, OR. find our card
  8. Cai, Jie and Michael Strube. 2010. End-to-end coreference resolution via hypergraph partitioning. In Proceedings of the International Conference on Computational Linguistics, pages 143–151, Stroudsburg, PA. find our card
  9. Chang, Kai-Wei, Rajhans Samdani, Alla Rozovskaya, Nick Rizzolo, Mark Sammons, and Dan Roth. 2011. Inference protocols for coreference resolution. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 40–44, Portland, OR. find our card
  10. Chen, Chen and Vincent Ng. 2012. Combining the best of two worlds: A hybrid approach to multilingual coreference resolution. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 56–63, Jeju Island. find our card
  11. Chu, Y. J. and T. H. Liu. 1965. On the shortest arborescence of a directed graph. Science Sinica, 14:1,396–1,400. find
  12. Collins, Michael. 2002. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1–8, Philadelphia, PA. find our card
  13. Culotta, Aron, Michael Wick, and Andrew Mccallum. 2007. First-order probabilistic models for coreference resolution. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 81–88, Rochester, NY. della Pietra,… find our card
  14. Denis, Pascal and Jason Baldridge. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 236–243, Rochester, N… find our card
  15. Denis, Pascal and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 660–669, Honolulu, HI. find our card
  16. Doddington, G., A. Mitchell, M. Przybocki, L. Ramshaw, S. Strassel, and R. Weischedel. 2004. The automatic content extraction (ACE) program—Tasks, data, and evaluation. In Proceedings of the International Conference on LREC, pages 837–840, Lisbon. dos Santos, Cı́cero Nogueira and Ruy L. Milidiú. 20… find our card
  17. Edmonds, J. 1967. Optimum branchings. Journal of Research of the National Bureau of Standards, 71B:233–240. find
  18. Fernandes, Eraldo R., Cı́cero Nogueira dos Santos, and Ruy L. Milidiú. 2012. Latent structure perceptron with feature induction for unrestricted coreference resolution. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 41–48, Jeju Island. find our card
  19. Fernandes, Eraldo R. and Ruy L. Milidiú. 2012. Entropy-guided feature generation for structured learning of Portuguese dependency parsing. In H. Caseli et al., editors, Proceedings of the Conference on Computational Processing of the Portuguese Language, volume 7243 of Lecture Notes in Computer Sci… find
  20. Fernandes, Eraldo R. and Ulf Brefeld. 2011. Learning from partially annotated sequences. In Dimitrios Gunopulos, Thomas Hofmann, Donato Malerba, and Michalis Vazirgiannis, editors, Machine Learning and Knowledge Discovery in Databases, volume 6911 of Lecture Notes in Computer Science. Springer, Berl… find
  21. Finkel, Jenny Rose and Christopher D. Manning. 2008. Enforcing transitivity in coreference resolution. In Proceedings of the Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers, pages 45–48, Columbus, OH. find our card
  22. Finley, Thomas and Thorsten Joachims. 2005. Supervised clustering with support vector machines. In Proceedings of the International Conference on Machine Learning, pages 217–224, New York, NY. find
  23. Haghighi, Aria and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1,152–1,161, Singapore. find our card
  24. Haghighi, Aria and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 385–393, Los Angeles, CA. find our card
  25. Klenner, Manfred. 2007. Enforcing consistency on coreference sets. In Proceedings of the International Conference on Recent Advances in Natural Language Processing, pages 323–328, Borovets. find
  26. Koo, Terry, Alexander M. Rush, Michael Collins, Tommi Jaakkola, and David Sontag. 2010. Dual decomposition for parsing with non-projective head automata. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1,288–1,298, Cambridge, MA. find
  27. Lee, Heeyoung, 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
  28. Lee, Heeyoung, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 28… find our card
  29. Luo, Xiaoqiang. 2005. On coreference resolution performance metrics. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 25–32, Vancouver. find our card
  30. Luo, Xiaoqiang, Abe Ittycheriah, Hongyan Jing, Nanda Kambhatla, and Salim Roukos. 2004. A mention-synchronous coreference resolution algorithm based on the bell tree. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, ACL’04, pages 135–142, Stroudsburg, PA. find our card
  31. Martschat, Sebastian, Jie Cai, Samuel Broscheit, Éva Mújdricza-Maydt, and Michael Strube. 2012. A multigraph model for coreference resolution. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 100–106, Jeju Island. find
  32. McCallum, Andrew. 2003. Efficiently inducing features of conditional random fields. In Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence, UAI’03, pages 403–410, San Francisco, CA. find
  33. McCallum, Andrew and Ben Wellner. 2005. Conditional models of identity uncertainty with application to noun coreference. In Lawrence K. Saul, Yair Weiss, and Léon Bottou, editors, Proceedings of the Advances in Neural Information Processing Systems 17. MIT Press, Cambridge, MA, pages 905–912. find
  34. McCarthy, Joseph F. and Wendy G. Lehnert. 1995. Using decision trees for coreference resolution. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pages 1,050–1,055, Montreal. find
  35. McDonald, Ryan, Koby Crammer, and Fernando Pereira. 2005. Online large-margin training of dependency parsers. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 91–98, Ann Arbor, MI. find our card
  36. McDonald, Ryan and Fernando Pereira. 2006. Online learning of approximate dependency parsing algorithms. In Proceedings of the 11st Conference of the European Chapter of the Association for Computational Linguistics, pages 81–88, Trento. find our card
  37. Milidiú, Ruy Luiz, Cı́cero Nogueira dos Santos, and Julio C. Duarte. 2008. Phrase chunking using entropy guided transformation learning. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 647–655, Columbus, OH. find
  38. Ng, Vincent. 2009. Graph-cut-based anaphoricity determination for coreference resolution. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 575–583,Boulder, CO. find our card
  39. Ng, Vincent. 2010. Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1,396–1,411, Uppsala. find our card
  40. Ng, Vincent and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 104–111, Philadelphia, PA. find our card
  41. Ponzetto, Simone Paolo and Michael Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 192–199, New York,… find our card
  42. Poon, Hoifung and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov logic. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 650–659, Honolulu, HI. find our card
  43. Pradhan, Sameer, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 Shared Task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL—Shared Task, CoNLL’12, pages 1–40, Jeju Island. find our card
  44. Pradhan, Sameer, 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 Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 1–27, Portland. find our card
  45. Quinlan, J. Ross. 1992. C4.5: Programs for Machine Learning (Morgan Kaufmann Series in Machine Learning). Morgan Kaufmann, 1st edition. find our card
  46. Rahman, Altaf and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 968–977, Singapore. find our card
  47. Rosenblatt, Frank. 1957. The Perceptron— A perceiving and recognizing automaton. Technical report 85-460-1, Cornell Aeronautical Laboratory. find
  48. Sapena, Emili, Lluı́s Padró, and Jordi Turmo. 2010. Relaxcor: A global relaxation labeling approach to coreference resolution. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 88–91, Los Angeles, CA. find our card
  49. Sapena, Emili, Lluı́s Padró, and Jordi Turmo. 2011. Relaxcor participation in CoNLL Shared Task on coreference resolution. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 35–39, Portland, OR. find our card
  50. Sapena, Emili, Lluı́s Padró, and Jordi Turmo. 2013. A constraint-based hypergraph partitioning approach to coreference resolution. Computational Linguistics, 39(4):847–884. find our card
  51. Soon, Wee Meng, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27:521–544. find our card
  52. Stoyanov, Veselin, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Coreference resolution with reconcile. In Proceedings of the Annual Meeting of the Association for Computational Linguistics: Short Papers, pages 156–161, Uppsala. find our card
  53. Stoyanov, Veselin, Nathan Gilbert, Claire Cardie, and Ellen Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-ofthe-art. In Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th Internationa… find
  54. Su, Jiang and Harry Zhang. 2006. A fast decision tree learning algorithm. In Proceedings of the 21st National Conference on Artificial intelligence, pages 500–505, Boston, MA. find
  55. Sun, Xu, Takuya Matsuzaki, Daisuke Okanohara, and Jun’ichi Tsujii. 2009. Latent variable perceptron algorithm for structured classification. In Proceedings of the 21st International Joint Conference on Artificial Intelligence, pages 1,236–1,242, Pasadena, CA. find
  56. Sundheim, Beth and Ralph Grishman. 1995. Appendix D: Coreference task definition (v2.3). In Proceedings of the 6th Conference on Message Understanding, pages 333–344, Columbia, MD. find
  57. Tsochantaridis, I., Thorsten Joachims, T. Hofmann, and Y. Altun. 2005. Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6:1453–1484. find
  58. Uryupina, Olga, Alessandro Moschitti, and Massimo Poesio. 2012. BART goes multilingual: The UniTN/Essex submission to the CoNLL-2012 Shared Task. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 122–128, Jeju Island. find
  59. Uryupina, Olga, Sriparna Saha, Asif Ekbal, and Massimo Poesio. 2011. Multi-metric optimization for coreference: The UniTN/IITP/Essex submission to the 2011 CoNLL Shared Task. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 61–65, Portland, OR… find our card
  60. Vilain, Marc, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Conference on Message Understanding, pages 45–52, Columbia, MD. find our card
  61. Weischedel, Ralph, Eduard Hovy, Mitchell Marcus, Martha Palmer, Robert Belvin, Sameer Pradhan, Lance Ramshaw, and Nianwen Xue. 2011. OntoNotes: A large training corpus for enhanced processing. In Joseph Olive, Caitlin Christianson, and John McCary, editors, Handbook of Natural Language Processing an… find
  62. Yang, Xiaofeng, 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 Annual Meeting of the Association for Computational Linguistics, pages 843–851, Columbus, OH. find our card
  63. Yang, Xiaofeng, Jian Su, and Chew Lim Tan. 2008. A twin-candidate model for learning-based anaphora resolution. Computational Linguistics, 34(3):327–356. find our card
  64. Yang, Xiaofeng, Guodong Zhou, Jian Su, and Chew Lim Tan. 2003. Coreference resolution using competition learning approach. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 176–183, Sapporo. find our card
  65. Yu, Chun-Nam John and Thorsten Joachims. 2009. Learning structural SVMS with latent variables. In Proceedings of the 26th Annual International Conference on Machine Learning, ICML’09, pages 1,169–1,176, New York, NY. find
  66. Yuan, Bo, Qingcai Chen, Yang Xiang, Xiaolong Wang, Liping Ge, Zengjian Liu, Meng Liao, and Xianbo Si. 2012. A mixed deterministic model for coreference resolution. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning: Shared Task, pages 76–82, Jeju Island. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/fernandes-2014-latent-trees-coreference-resolution/