Elamur Research⌕
☰
home / papers / 2018 / Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

Summary

Event coreference resolution, which means linking mentions of the same real-world event, lags far behind entity coreference. One reason is that coreferent event mentions are scarce and spread across distant sentences, so local lexical and argument cues often fail. Choubey and Huang observe that events tend to be repeated for content organization, so their repetition tracks a document's topic layout. Their approach casts coreference resolution as an optimization solved with Integer Linear Programming (ILP). Pairwise probabilities from a neural local classifier feed an objective with transitivity constraints. Extra terms and constraints then encode four structural signals:

  • main event chains appearing in topic transition sentences, plus a preference against fragmented chains;
  • co-occurrence across semantically associated chains;
  • the news-genre tendency for chains to begin early in a document;
  • specific-action subevents, which are seldom referred back to.

On KBP 2016 and KBP 2017, the full model beats a greedy local classifier, spectral clustering and the joint model of Lu and Ng (2017) across standard metrics. The work shows that discourse-level structure can recover links that local features miss.

Key points

  • Corpus statistics on richERE and ACE-05 motivate the approach. Roughly 70% of entity mentions have their nearest antecedent in the same or previous sentence. Only about 10% of coreferent event pairs share a sentence.
  • Compared with the local classifier baseline, average F1 rose by 3.1 on KBP 2016 and 2.17 on KBP 2017. MUC F1 improved by more than 28%.
  • On KBP 2016, the system surpasses the previous best model (Lu and Ng, 2017) on every metric, by 1.21 average F1.
  • Structures were added one at a time to the ILP: Topic structure, Cross-chain, Distribution, then Subevent (Full). On KBP 2016, every component helped MUC and BLANC.
  • Subevent constraints slightly lowered KBP 2017 scores. The authors attribute this to their simple subevent extraction, which found only 31 subevents in KBP 2017 versus 211 in KBP 2016.

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

14 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 6 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p18-1045

@inproceedings{choubey2018improving,
  title = {{Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures}},
  author = {Choubey, Prafulla Kumar and Huang, Ruihong},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1045},
  url = {https://doi.org/10.18653/v1/p18-1045}
}

References

44 references, 26 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. Association for Computational Linguistics, Stroudsburg, PA, USA, ARTE ’06, pages 1–8. http://dl.acm.org/citation.cfm?id=1629235.1629236. ↗
  2. Jun Araki, Zhengzhong Liu, Eduard H Hovy, and Teruko Mitamura. 2014. Detecting subevent structure for event coreference resolution. In LREC. pages 4553–4558. find our card
  3. Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, and Andrej Risteski. 2016. A latent variable model approach to pmi-based word embeddings. Transactions of the Association for Computational Linguistics 4:385–399. find
  4. Allison Badgett and Ruihong Huang. 2016. Extracting subevents via an effective two-phase approach. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. pages 906–911. the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers… find
  5. Agata Cybulska and Piek Vossen. 2014. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In LREC. pages 4545– 4552. find our card
  6. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference. Granada, volume 1, pages 563–566. find our card
  7. Agata Cybulska and Piek Vossen. 2015a. Translating granularity of event slots into features for event coreference resolution. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation. pages 1–10. find our card
  8. Cosmin Adrian 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. Association for Computational Linguistics, pages 1412–1422. find our card
  9. A.K. Cybulska and P.T.J.M. Vossen. 2015b. Bag of events approach to event coreference resolution. supervised classification of event templates. Lecture Notes in Computer Science (9042). 978-3-319-18117-2. find
  10. Cosmin Adrian Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. Computational Linguistics 40(2):311–347. find our card
  11. Pascal Denis, Jason Baldridge, et al. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In HLT-NAACL. pages 236–243. find our card
  12. 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. Association for Computational Linguistics, pages 54–57. find our card
  13. Joe Ellis, Jeremy Getman, Dana Fore, Neil Kuster, Zhiyi Song, Ann Bies, and Stephanie Strassel. 2015. Overview of linguistic resources for the tac kbp 2015 evaluations: Methodologies and results. In Proceedings of TAC KBP 2015 Workshop, National Institute of Standards and Technology. pages 16–17. find
  14. Zheng Chen, Heng Ji, and Robert Haralick. 2009. A pairwise event coreference model, feature impact and evaluation for event coreference resolution. In Proceedings of the workshop on events in emerging text types. Association for Computational Linguistics, pages 17–22. find our card
  15. Joe Ellis, Jeremy Getman, Neil Kuster, Zhiyi Song, Ann Bies, and Stephanie Strassel. 2016. Overview of linguistic resources for the tac kbp 2016 evaluations: Methodologies and results. In Proceedings of TAC KBP 2016 Workshop, National Institute of Standards and Technology. find
  16. Prafulla Kumar Choubey and Ruihong Huang. 2017a. Event coreference resolution by iteratively unfolding inter-dependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. pages 2124–2133. find our card
  17. Prafulla Kumar Choubey and Ruihong Huang. 2017b. Tamu at kbp 2017: Event nugget detection and coreference resolution. In Proceedings of TAC KBP 2017 Workshop, National Institute of Standards and Technology. find
  18. Jenny Rose Finkel and Christopher D Manning. 2008. Enforcing transitivity in coreference resolution. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers. Association for Computational Linguistics, pages 45–48. find our card
  19. Prafulla Kumar Choubey, Kaushik Raju, and Ruihong Huang. 2018. Identifying the most dominant event in a news article by mining event coreference relations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologie… find our card
  20. Jeremy Getman, Joe Ellis, Zhiyi Song, Jennifer Tracey, and Stephanie Strassel. 2017. Overview of linguistic resources for the tac kbp 2017 evaluations: Methodologies and results. In Proceedings of TAC KBP 2017 Workshop, National Institute of Standards and Technology. find
  21. Barbara J Grosz, Scott Weinstein, and Aravind K Joshi. 1995. Centering: A framework for modeling the local coherence of discourse. Computational linguistics 21(2):203–225. find our card
  22. Kevin Clark and Christopher D Manning. 2016a. Deep reinforcement learning for mention-ranking coreference models. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. pages 2256–2262. find our card
  23. Aria Haghighi and Dan Klein. 2007. Unsupervised coreference resolution in a nonparametric bayesian model. In Proceedings of the 45th annual meeting of the association of computational linguistics. pages 848–855. find our card
  24. Kevin Clark and Christopher D Manning. 2016b. Improving coreference resolution by learning entity-level distributed representations. In Proceedings of for python. The University of Auckland, Auckland, New Zealand, http://www.optimization-online. org/DB FILE/2011/09/3178. pdf . ↗ 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. Nafise Sadat Moosavi and Michael Strube. 2017. Lexical features in coreference resolution: To be used with caution. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). volume 2, pages 14–19. find our card
  27. 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. Association… find our card
  28. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12:2825… find
  29. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. pages 188–197. find our card
  30. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Empirical Methods in Natural Language Processing (EMNLP). pages 1532– 1543. http://www.aclweb.org/anthology/D14-1162. ↗
  31. Zhengzhong Liu, Jun Araki, Eduard H Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In LREC. pages 4539–4544. find our card
  32. Marta Recasens and Eduard Hovy. 2011. Blanc: Implementing the rand index for coreference evaluation. Natural Language Engineering 17(4):485– 510. find
  33. Jing Lu and Vincent Ng. 2017. Joint learning for event coreference resolution. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). volume 1, pages 90–101. find
  34. Zhiyi Song, Ann Bies, Stephanie Strassel, Tom Riese, Justin Mott, Joe Ellis, Jonathan Wright, Seth Kulick, Neville Ryant, and Xiaoyi Ma. 2015. From light to rich ere: annotation of entities, relations, and events. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference,… find
  35. Jing Lu, Deepak Venugopal, Vibhav Gogate, and Vincent Ng. 2016. Joint inference for event coreference resolution. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. pages 3264–3275. find our card
  36. Marc Vilain, 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. Association for Computational Linguistics, pages 45–52. find our card
  37. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the conference on human language technology and empirical methods in natural language processing. Association for Computational Linguistics, pages 25–32. find our card
  38. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Association for Computational Linguistics (ACL) System Demonstrations. pages 55–60. http://www.aclweb.org/anthology/P/P14/P14-50… ↗ our card
  39. Christopher Walker, Medero Strassel, Maeda Julie, and Kazuaki. 2006. find
  40. Ace 2005 multilingual training corpus. In Linguistic Data Consortium, LDC Catalog No.: LDC2006T06.. find
  41. Bishan Yang, Claire Cardie, and Peter Frazier. 2015. A hierarchical distance-dependent bayesian model for event coreference resolution. Transactions of the Association of Computational Linguistics 3(1):517– 528. find
  42. Sebastian Martschat and Michael Strube. 2015. Latent structures for coreference resolution. Transactions of the Association of Computational Linguistics 3(1):405–418. find our card
  43. Teruko Mitamura, Zhengzhong Liu, and Eduard Hovy. 2017. Events detection, coreference and sequencing: Whats next? overview of the tac kbp 2017 event track. In Proceedings of TAC KBP 2017 Workshop, National Institute of Standards and Technology. find
  44. Stuart Mitchell, Michael OSullivan, and Iain Dunning. 2011. Pulp: a linear programming toolkit find

↑ back to top

This page in Markdown →