Elamur Research⌕
☰
home / papers / 2014 / Unsupervised Event Coreference Resolution

Unsupervised Event Coreference Resolution

Summary

The paper addresses event coreference resolution, which means grouping textual mentions that refer to the same real-world event, both within a single document and across documents. Earlier systems relied on supervised pairwise classifiers that depend on labeled data from a particular domain and make only local decisions. The authors instead propose fully unsupervised, nonparametric Bayesian models that infer the number of event clusters from unlabeled text. Each mention is described by many automatically extracted lexical, syntactic and semantic features, such as participants, location and time.

The first model extends the hierarchical Dirichlet process (HDP) so that it can handle any finite number of features per mention. The second is a hybrid, iFHMM–iHMM, which pairs a discrete time-series model with a latent class model that permits infinitely many classes. It learns how many features to use, selects the most informative ones, and takes into account the order of mentions within a document.

The models were evaluated on ACE, OntoNotes and a newly annotated corpus, ECB. Both models clearly outperform two baselines. This matters because it shows that event coreference can be handled without costly annotation.

Key points

  • Two models are proposed: an HDP extension for multi-feature mentions and the hybrid iFHMM–iHMM with automatic feature selection.
  • The authors created ECB, a corpus annotated for both within- and cross-document event coreference. ACE and OntoNotes were also used.
  • Mentions are described by up to 132 feature types. The iFHMM–iHMM stays competitive while keeping only about 2% of the feature values.
  • Results are reported with MUC, B³, CEAF and pairwise (PW) metrics. On ECB within-document coreference, feature sampling raised B³ F1 from 73.6 (all features) to 89.4.
  • Common errors come from partonomic links between participants and places (e.g., a warship and its navy). The authors plan to use WordNet meronymy and hypernymy to address them.

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

25 papers of our library cite it (of the 140673 whose bibliographies we read); 13 of them have a page here, 12 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00174

@article{bejan2014unsupervised,
  title = {{Unsupervised Event Coreference Resolution}},
  author = {Bejan, Cosmin Adrian and Harabagiu, Sanda},
  journal = {Computational Linguistics},
  year = {2014},
  doi = {10.1162/coli\_a\_00174},
  url = {https://doi.org/10.1162/coli_a_00174}
}

References

83 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ahn, David. 2006. The stages of event extraction. In Proceedings of the Workshop on Annotating and Reasoning about Time and Events, pages 1–8, Sydney. find
  2. Allan, James, editor. 2002. Topic Detection and Tracking: Event-Based Information Organization. Kluwer Academic Publishers. find
  3. Allan, James, Jaime Carbonell, George Doddington, Jonathan Yamron, and Yiming Yang. 1998. Topic detection and tracking pilot study: Final report. In Proceedings of the Broadcast News Understanding and Transcription Workshop, pages 194–218, Lansdowne, VA. find
  4. Bagga, Amit and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the 1st International Conference on Language Resources and Evaluation (LREC-1998), pages 563–566, Granada. find our card
  5. Bagga, Amit and Breck Baldwin. 1999. Cross-document event coreference: Annotations, experiments, and observations. In Proceedings of the ACL Workshop on Coreference and its Applications, pages 1–8, College Park, MD. find our card
  6. Baker, Collin F., 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 17th International Conference on Computational Linguistics (COLING-ACL), pages 86–90, Montreal. find our card
  7. Beal, Matthew J., Zoubin Ghahramani, and Carl Edward Rasmussen. 2002. The infinite hidden Markov model. In Advances in Neural Information Processing Systems 14 (NIPS), pages 577–584, Vancouver. find
  8. Bejan, Cosmin Adrian. 2007. Deriving chronological information from texts through a graph-based algorithm. In Proceedings of the 20th Florida Artificial Intelligence Research Society International Conference (FLAIRS), Applied Natural Language Processing Track, pages 259–260, Key West, FL. find
  9. Bejan, Cosmin Adrian. 2008. Unsupervised discovery of event scenarios from texts. In Proceedings of the 21st Florida Artificial Intelligence Research Society International Conference (FLAIRS), Applied Natural Language Processing Track, pages 124–129, Coconut Grove, FL. find
  10. Bejan, Cosmin Adrian and Sanda Harabagiu. 2008a. A linguistic resource for discovering event structures and resolving event coreference. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC), pages 2,881–2,887, Marrakech. find our card
  11. Bejan, Cosmin Adrian and Sanda Harabagiu. 2008b. Using clustering methods for discovering event structures. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), pages 1,776–1,777, Chicago, IL. find
  12. Bejan, Cosmin Adrian 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 (ACL), pages 1,412–1,422, Uppsala. find our card
  13. Bejan, Cosmin Adrian and Chris Hathaway. 2007. UTD-SRL: A pipeline architecture for extracting frame semantic structures. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval), pages 460–463, Prague. find our card
  14. Bejan, Cosmin Adrian, Matthew Titsworth, Andrew Hickl, and Sanda Harabagiu. 2009. Nonparametric Bayesian models for unsupervised event coreference resolution. In Advances in Neural Information Processing Systems 23 (NIPS), pages 73–81, Vancouver. find
  15. Blei, David, Andrew Ng, and Michael Jordan. 2003. Latent Dirichlet allocation. Journal of Machine Learning Research, pages 993–1,022. find our card
  16. Boyd-Graber, Jordan, David Blei, and Xiaojin Zhu. 2007. A topic model for word sense disambiguation. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 1,024–1,033, Prague. find
  17. Bryant, Michael and Erik B. Sudderth. 2012. Truly nonparametric online variational inference for hierarchical Dirichlet processes. In Advances in Neural Information Processing Systems 25 (NIPS), pages 2,708–2,716, Lake Tahoe, NV. find
  18. Cardie, Claire and Kiri Wagstaf. 1999. Noun phrase coreference as clustering. In Proceedings of the 1999 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 82–89, College Park, MD. find our card
  19. Chen, Bin, Jian Su, and Chew Lim Tan. 2010a. A twin-candidate based approach for event pronoun resolution using composite kernel. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING), pages 188–196, Beijing. find
  20. Chen, Bin, Jian Su, and Chew Lim Tan. 2010b. Resolving event noun phrases to their verbal mentions. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 872–881, Cambridge, MA. find
  21. Chen, Zheng 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, Singapore. find our card
  22. Chu, Wei, Zoubin Ghahramani, Roland Krause, and David Wild. 2006. Identifying protein complexes in high-throughput protein interaction screens using an infinite latent feature model. In Pacific Symposium on Biocomputing (PSB-11), pages 231–242, Maui, HI. find
  23. Cowans, Philip. 2004. Information retrieval using hierarchical Dirichlet processes. In Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 564–565, Sheffield. find
  24. Daumé III, Hal. 2007. Frustratingly easy domain adaptation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL), pages 256–263, Prague. find
  25. Daumé III, Hal and Daniel Marcu. 2005. A Bayesian model for supervised clustering with the Dirichlet process prior. Journal of Machine Learning Research (JMLR), 6:1551–1577. find
  26. Davidson, Donald, 1969. The individuation of events, pages 216–234. In N. Rescher et al., editors, Essays in Honor of Carl G. Hempel. Dordrecht: Reidel. Reprinted in D. Davidson, editor, Essays on Actions and Events. 2001, Oxford: Clarendon Press. find
  27. Davidson, Donald, 1985. Reply to Quine on Events. In E. LePore and B. McLaughlin, eds., Actions and Events: Perspectives on the Philosophy of Donald Davidson. Blackwell, Oxford, pages 172–176. de Marneffe, Marie-Catherine, Anna N. Rafferty, and Christopher D. Manning. 2008. Finding contradictions in… find
  28. Denis, Pascal and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP’08), pages 660–669, Honolulu, HI. find our card
  29. Doshi-Velez, Finale. 2009. The Indian Buffet Process: Scalable Inference and Extensions. Ph.D. thesis, Department of Engineering, University of Cambridge. find
  30. Fellbaum, Christiane. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA. find
  31. Ferguson, Thomas S. 1973. A Bayesian analysis of some nonparametric problems. The Annals of Statistics, 1(2):209–230. find
  32. Finkel, Jenny Rose, Trond Grenager, and Christopher Manning. 2007. The infinite tree. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, pages 272–279, Prague. find
  33. Finkel, Jenny Rose and Christopher Manning. 2008. Enforcing transitivity in coreference resolution. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT), Short Papers, pages 45–48, Columbus, OH. find our card
  34. Fox, E. B., E. B. Sudderth, and A. S. Willsky. 2007. Hierarchical Dirichlet processes for tracking maneuvering targets. In Proceedings of International Conference on Information Fusion, pages 1,415–1,422, Quebec. find
  35. Geman, Stuart and Donald Geman. 1984. Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6:721–741. find
  36. Ghahramani, Zoubin, T. L. Griffiths, and Peter Sollich, 2007. Bayesian Nonparametric Latent Feature Models. In Bayesian Statistics 8, edited by J. M. Bernardo et al., pages 201–225. Oxford University Press. find
  37. Ghahramani, Zoubin and Michael Jordan. 1997. Factorial hidden Markov models. Machine Learning, 29:245–273. find
  38. Goldwater, Sharon, Thomas L. Griffiths, and Mark Johnson. 2006. Contextual dependencies in unsupervised word segmentation. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 673–680, Sydney. find
  39. Görür, Dilan, Frank Jäkel, and Carl Edward Rasmussen. 2006. A choice model with infinitely many latent features. In Proceedings of the 23rd Annual International Conference on Machine Learning (ICML), pages 361–368, Pittsburgh, PA. find
  40. Griffiths, Thomas and Mark Steyvers. 2004. Finding scientific topics. In Proceedings of the National Academy of Sciences, pages 5,228–5,235. find
  41. Griffiths, Tom and Zoubin Ghahramani. 2005. Infinite latent feature models and the Indian buffet process. Technical Report 2005-10, Gatsby Computational Neuroscience Unit, University College London. find
  42. Griffiths, Tom and Zoubin Ghahramani. 2006. Infinite latent feature models and the indian buffet process. In Advances in Neural Information Processing Systems 18 (NIPS), pages 475–482, Vancouver. find
  43. Haghighi, Aria and Dan Klein. 2007. Unsupervised coreference resolution in a nonparametric Bayesian model. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL), pages 848–855, Prague. find our card
  44. Haghighi, Aria and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1,152–1,161, Singapore. find our card
  45. Haghighi, Aria and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 385–393, Los Angeles, CA. find our card
  46. Haghighi, Aria, Andrew Ng, and Christopher Manning. 2005. Robust textual inference via graph matching. find
  47. In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP), pages 387–394, Vancouver. find
  48. Hasler, Laura and Constantin Orasan. 2009. Do coreferential arguments make event mentions coreferential? In Proceedings of the 7th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC 2009), pages 151–163, Goa. find
  49. He, Tian. 2007. Coreference resolution on entities and events for hospital discharge summaries. Master’s thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology. find
  50. Humphreys, Kevin, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In Proceedings of the Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, 35th Meeting of ACL, pages 75–81, Madrid. find our card
  51. Kong, Fang and Guodong Zhou. 2011. Improve tree kernel-based event pronoun resolution with competitive information. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI), pages 1,814–1,819, Barcelona. find
  52. LDC-ACE. 2005. ACE (Automatic Content Extraction) English Annotation Guidelines for Events, version 5.4.3 2005.07.01. LDC Catalog Number: LDC2006T06. find
  53. LDC-ON. 2007. OntoNotes Release 2.0. LDC Catalog Number: LDC2008T04. find
  54. Lee, Heeyoung, 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
  55. Li, Fei-Fei and Pietro Perona. 2005. A Bayesian hierarchical model for learning natural scene categories. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) - Volume 2, pages 524–531, San Diego, CA. find
  56. Liang, Percy, Slav Petrov, Michael Jordan, and Dan Klein. 2007. The infinite PCFG using hierarchical Dirichlet processes. In Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL), pages 688–697, Prague. find
  57. Lowe, John B., Collin F. Baker, and Charles J. Fillmore. 1997. A frame-semantic approach to semantic annotation. In Proceedings of the SIGLEX Workshop on Tagging Text with Lexical Semantics: Why, What, and How?, pages 18–24, Washington, DC. find our card
  58. Luo, Xiaoqiang. 2005. On coreference resolution performance metrics. In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP-2005), pages 25–32, Vancouver. find our card
  59. 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 Meeting of the Association for Computational Linguistics (ACL’04), Main Volume, pages 135–142, Barcelona. find our card
  60. Malpas, Jeff. 2009. Donald Davidson. In the Stanford Encyclopedia of Philosophy (Fall 2009 Edition), edited by Edward N. Zalta. Available at http://plato.stanford.edu/archives/fall2009/entries/davidson/. ↗
  61. Meeds, Edward, Zoubin Ghahramani, Radford Neal, and Sam Roweis. 2006. Modeling dyadic data with binary latent factors. In Advances in Neural Information Processing Systems 19 (NIPS), pages 977–984, Vancouver. find
  62. Miller, Kurt, Thomas Griffiths, and Michael Jordan. 2008. The phylogenetic Indian buffet process: A non-exchangeable nonparametric prior for latent features. In Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI), pages 403–410, Helsinki. find
  63. Narayanan, Srini and Sanda Harabagiu. 2004. Question answering based on semantic structures. In Proceedings of the 20th International Conference on Computational Linguistics (COLING), pages 693–701, Geneva. find
  64. Neal, Radford M. 2003. Slice Sampling. The Annals of Statistics, 31:705–741. find
  65. Ng, Vincent. 2008. Unsupervised models for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 640–649, Honolulu, HI. find our card
  66. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–105. find our card
  67. Poon, Hoifung and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov logic. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 650–659, Honolulu, HI. find our card
  68. Pustejovsky, James, Jose Castano, Bob Ingria, Roser Sauri, Rob Gaizauskas, Andrea Setzer, and Graham Katz. 2003a. TimeML: Robust specification of event and temporal expressions in text. In Proceedings of the Fifth International Workshop on Computational Semantics (IWCS), pages 337–353, Tilburg. find
  69. Pustejovsky, James, Patrick Hanks, Roser Sauri, Andrew See, Robert Gaizauskas, Andrea Setzer, Dragomir Radev, Beth Sundheim, David Day, Lisa Ferro, and Marcia Lazo. 2003b. The TimeBank Corpus. In Corpus Linguistics, pages 647–656. find
  70. Quine, W. V. O., 1985. Events and Reification. In E. LePore and B. P. McLaughlin, editors, Actions and Events: Perspectives on the Philosophy of Donald Davidson. Blackwell, Oxford, pages 162–171. Reprinted in R. Casati and A. C. Varzi, editors, Events. 1996, Aldershot, Dartmouth, pages 107–116. find
  71. Rabiner, Lawrence R. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. In Proceedings of the IEEE, pages 257–286. find
  72. Raghunathan, Karthik, Heeyoung Lee, Sudarshan Rangarajan, Nate Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 492–501, Cambr… find our card
  73. Rahman, Altaf and Vincent Ng. 2011. Coreference resolution with world knowledge. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 814–824, Portland, OR. find our card
  74. Reisinger, Joseph and Marius Paşca. 2009. Latent variable models of concept-attribute attachment. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 620–628, Singapore. find
  75. Sivic, Josef, Bryan Russell, Alexei Efros, Andrew Zisserman, and William Freeman. 2005. Discovering object categories in image collections. In Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV), pages 370–377, Beijing. find
  76. Sivic, Josef, Bryan Russell, Andrew Zisserman, William Freeman, and Alexei Efros. 2008. Unsupervised discovery of visual object class hierarchies. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8, Anchorage, AK. find
  77. Stoyanov, Veselin, 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 ACL and the 4th International Joint Conference on Natural Languag… find our card
  78. Sudderth, Erik B., Antonio Torralba, William T. Freeman, and Alan S. Willsky. 2008. Describing visual scenes using transformed objects and parts. International Journal of Computer Vision, 77:291–330. find
  79. Teh, Yee Whye, Michael Jordan, Matthew Beal, and David Blei. 2006. Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101(476):1566–1581. find
  80. Van Gael, Jurgen, Y. Saatci, Yee Whye Teh, and Zoubin Ghahramani. 2008. Beam sampling for the infinite hidden Markov model. In Proceedings of the 25th Annual International Conference on Machine Learning (ICML), pages 1,088–1,095, Helsinki. find
  81. Van Gael, Jurgen, Yee Whye Teh, and Zoubin Ghahramani. 2008. The infinite factorial hidden Markov model. In Advances in Neural Information Processing Systems 21 (NIPS), pages 1697–1704, Vancouver. find
  82. Vilain, Marc, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of MUC-6, pages 45–52, Columbia, MD. find our card
  83. Wang, Chong, John Paisley, and David Blei. 2011. Online variational inference for the hierarchical Dirichlet process. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), pages 752–760, Ft. Lauderdale, FL. find

↑ back to top

This page in Markdown →