Elamur Research⌕
☰
home / papers / 2015 / Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

Summary

Resolving which event mentions in a document describe the same real-world happening is hard. It is even harder for Chinese, which has received little research attention and lacks large lexical resources comparable to WordNet or FrameNet, which have helped English systems. Chen and Ng address within-document Chinese event coreference in the ACE 2005 setting without any training data labeled with coreference links. They design a generative probabilistic model whose parameters are estimated with EM on raw text, treating the true antecedent as a hidden variable. The model scores candidate antecedents using trigger-word pairs and context features, which are assumed conditionally independent. It also decides jointly whether a mention is anaphoric at all, through a dummy antecedent. This matters because only about a quarter of event mentions corefer with an earlier one. On the Chinese portion of ACE 2005, the unsupervised system significantly outperforms SinoCoreferencer, a state-of-the-art supervised resolver. Because the method is language-independent and needs no knowledge bases, it could transfer to low-resource languages.

Key points

  • Data and setting: The model is evaluated on the Chinese part of the ACE 2005 corpus. ACE 2005 defines 8 event types and 33 subtypes, and only 24.4% of Chinese event mentions in it are anaphoric.
  • Method: The generative model estimates P(e, k, c, l), with antecedent correctness l treated as latent and learned via EM. Non-anaphoric mentions are handled by linking them to a dummy candidate antecedent.
  • Main evidence of coreference: The model relies on trigger similarity, specifically BV matches and word2vec similarity. A candidate link is blocked when non-coreference conditions hold.
  • Comparison with SinoCoreferencer: On 323 mentions where the two systems disagree, the unsupervised model is correct in 205 cases and SinoCoreferencer in 118. The unsupervised model is especially better at leaving singletons and non-event mentions unresolved, which explains its higher precision.
  • Remaining errors: Most errors come from upstream pipeline components, including trigger and argument extraction and entity coreference, as well as from unmodeled attributes such as Modality, Polarity, Genericity, Tense and timing. The authors propose joint inference across these components 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

6 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 5 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/n15-1116

@inproceedings{chen2015chinese,
  title = {{Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers}},
  author = {Chen, Chen and Ng, Vincent},
  booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2015},
  doi = {10.3115/v1/n15-1116},
  url = {https://doi.org/10.3115/v1/n15-1116}
}

References

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

  1. David Ahn. 2006. The stages of event extraction. In Proceedings of the Workshop on Annotating and Reasoning about Time and Events, pages 1--8. find
  2. Jun Araki, Zhengzhong Liu, Eduard Hovy, and Teruko Mitamura. 2014. Detecting subevent structure for event coreference resolution. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4553--4558. find our card
  3. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the Linguistic Coreference Workshop at the First International Conference on Language Resources and Evaluation, page 563--566. find our card
  4. Amit Bagga and Breck Baldwin. 1999. Cross-document event coreference: Annotation, experiments, and observations. In Proceedings of the ACL Workshop on Coreference and Its Applications, pages 1--9. find
  5. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, Volume 1, pages 86--90. find our card
  6. Cosmin Bejan and Sanda Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1412--1422. find our card
  7. Cosmin Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. Computational Linguistics, 40(2):311--347. find our card
  8. Shane Bergsma and David Yarowsky. 2011. NADA: A robust system for non-referential pronoun detection. In Proceedings of the 8th Discourse Anaphora and Anaphor Resolution Colloquium, pages 12--23. find
  9. Zheng Chen and Heng Ji. 2009. Graph-based event coreference resolution. In Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-4), pages 54--57. find our card
  10. Chen Chen and Vincent Ng. 2014. SinoCoreferencer: An end-to-end Chinese event coreference resolver. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4532--4538. find our card
  11. Bin Chen, Jian Su, Sinno Jialin Pan, and Chew Lim Tan. 2011. A unified event coreference resolution by integrating multiple resolvers. In Proceedings of the 5th International Joint Conference on Natura Language Processing, pages 102--110. find our card
  12. Agata Cybulska and Piek Vossen. 2012. Using semantic relations to solve event coreference in text. In Proceedings of the LREC Workshop on Semantic Relations-II Enhancing Resources and Applications (SemRel 2012), pages 60--67. find
  13. Arthur P. Dempster, Nan M. Laird, and Donald B. Rubin. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 39:1--38. find
  14. Aymen Elkhlifi and Rim Faiz. 2009. Automatic annotation approach of events in news articles. International Journal of Computing and Information Sciences, 7(1):40--50. find
  15. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA. find
  16. Kartik Goyal, Sujay Kumar Jauhar, Huiying Li, Mrinmaya Sachan, Shashank Srivastava, and Eduard Hovy. 2013. A structured distributional semantic model for event co-reference. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: Volume 2 (Short Papers), pages 467… find our card
  17. Eduard Hovy, Teruko Mitamura, Felisa Verdejo, Jun Araki, and Andrew Philpot. 2013. Events are not simple: Identity, non-identity, and quasi-identity. In Proceedings of the NAACL-HLT Workshop on Events: Definition, Detection, Coreference, and Representation, pages 21--28. find
  18. Kevin Humphreys, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In Proceedings of the ACL/EACL Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pages 75--81. find our card
  19. Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 489--5… find our card
  20. Peifeng Li, Guodong Zhou, Qiaoming Zhu, and Libin Hou. 2012. Employing compositional semantics and discourse consistency in Chinese event extraction. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 100… find
  21. Zhengzhong Liu, Jun Araki, Eduard Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4539--4544. find our card
  22. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25-- 32. find our card
  23. Katie McConky, Rakesh Nagi, Moises Sudit, and William Hughes. 2012. Improving event co-reference by context extraction and dynamic feature weighting. In Proceedings of the 2012 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, pages 38… find
  24. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the Advances in Neural Information Processing Systems, pages 3111--3119. find
  25. Martina Naughton. 2009. Sentence Level Event Detection and Coreference Resolution. Ph.D. thesis, National University of Ireland, Dublin, Ireland. find
  26. Robert Parker, David Graff, Ke Chen, Junbo Kong, and Kazuaki Maeda. 2009. Chinese Gigaword fourth edition. Linguistic Data Consortium, Philadelphia, PA. find
  27. Sameer Pradhan, Lance Ramshaw, Ralph Weischedel, Jessica MacBride, and Linnea Micciulla. 2007. Unrestricted coreference: Identifying entities and events in OntoNotes. In Proceedings of the International Conference on Semantic Computing, pages 446--453. find
  28. 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 Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 1--27. find our card
  29. 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), pag… find our card
  30. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 968--977. find our card
  31. 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
  32. Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand Index for coreference evaluation. Natural Language Engineering, 17(4):485--510. find
  33. S. Sangeetha and Michael Arock. 2012. Event coreference resolution using mincut based graph clustering. In Proceedings of the Fourth International Workshop on Computer Networks & Communications, pages 253--260. find
  34. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the Sixth Message Understanding Conference, pages 45--52. find our card

↑ back to top

This page in Markdown →