Elamur Research⌕
☰
home / papers / 2021 / Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution

Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution

Summary

The paper addresses within-document event coreference resolution (ECR), which groups event mentions in a text by the real-world event they denote. The authors identify two weaknesses in earlier neural ECR systems. First, they model document-wide context poorly, using sparse hand-crafted features and ignoring how entities and context words relate. Second, they never use agreement between gold and predicted clusters as a training signal. The proposed model, StructECR, encodes text with BERT and builds a document graph whose nodes are context words, event mentions and entity mentions. Edges are weighted by discourse cues (sentence boundaries, coreference, mention spans), syntactic dependencies and semantic similarity. A GCN then enriches the mention representations before end-to-end resolution. Extra loss terms penalize inconsistencies between gold and predicted clusters. StructECR reports state-of-the-art results on KBP benchmarks. Ablations show that every component contributes, and the model transfers better across genres than its baselines. This matters because it shows that explicit document structure and cluster-level supervision improve event-level information extraction.

Key points

  • Encoding: BERT encodes documents in segments of 512 word-pieces. Entity mentions come from Stanford CoreNLP, and the predicted event mentions follow Choubey and Huang (2018) for comparability.
  • Graph edges: five interaction scores (sentence, span, coreference, dependency, semantic-based) are merged into a single adjacency matrix for the GCN. Keeping them as separate graphs ("GraphCombine" ablation) performs worse.
  • Regularization: three cluster-consistency terms (L_inner, L_inter, L_sim) are added to the training loss.
  • Ablations (KBP 2015 dev): the full model reaches 70.57 AVG F1. Every ablated variant drops to between roughly 66.9 and 69.6.
  • Cross-domain (AVG F1, newswire ↔ discussion forum on KBP 2016/2017): StructECR outperforms E2E-Only and Pairwise in every setup (p < 0.01).
    • KBP 2016, NW→DF: 68.19 vs 65.82 vs 60.51.
    • KBP 2017, DF→NW: 65.12 vs 62.52 vs 59.10.

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

12 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 10 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.acl-long.374

@inproceedings{tran2021exploiting,
  title = {{Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution}},
  author = {Tran, Hieu Minh and Phung, Duy and Nguyen, Thien Huu},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.374},
  url = {https://doi.org/10.18653/v1/2021.acl-long.374}
}

References

45 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Cosmin Adrian Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. In Computational Linguistics (CL). find our card
  2. David Ahn. 2006. The stages of event extraction. In Proceedings of the Workshop on Annotating and Reasoning about Time and Events. find
  3. Jun Araki and Teruko Mitamura. 2015. Joint event trigger identification and event coreference resolution with structured perceptron. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  4. Amit Bagga and Breck Baldwin. 1998. Entity-based cross-document coreferencing using the vector space model. In Proceedings of the International Conference on Computational Linguistics (COLING). find
  5. Shany Barhom, Vered Shwartz, Alon Eirew, Michael Bugert, Nils Reimers, and Ido Dagan. 2019. Revisiting joint modeling of cross-document entity and event coreference resolution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  6. Terra Blevins and Luke Zettlemoyer. 2020. Moving down the long tail of word sense disambiguation with gloss informed bi-encoders. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). find
  7. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2020. Streamlining cross-document coreference resolution: Evaluation and modeling. arXiv preprint arXiv:2009.11032. find
  8. Chen Chen and Vincent Ng. 2016. Joint inference over a lightly supervised information extraction pipeline: Towards event coreference resolution for resource-scarce languages. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI). find
  9. Zheng Chen and Heng Ji. 2009. Graph-based event coreference resolution. In Proceedings of the Workshop on Graph-based Methods for Natural Language Processing. find our card
  10. 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. find our card
  11. Prafulla Kumar Choubey and Ruihong Huang. 2017. Event coreference resolution by iteratively unfolding inter-dependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  12. Prafulla Kumar Choubey and Ruihong Huang. 2018. Improving event coreference resolution by modeling correlations between event coreference chains and document topic structures. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  13. Prafulla Kumar Choubey, Aaron Lee, Ruihong Huang, and Lu Wang. 2020. Discourse as a function of event: Profiling discourse structure in news articles around the main event. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). find
  14. Agata Cybulska and Piek T. J. M. Vossen. 2015. ”bag of events” approach to event coreference resolution. supervised classification of event templates. In Int. J. Comput. Linguistics Appl. find
  15. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies… find
  16. 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 (EMNLP). find our card
  17. Yin Jou Huang, Jing Lu, Sadao Kurohashi, and Vincent Ng. 2019. Improving event coreference resolution by learning argument compatibility from unlabeled data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… find
  18. Mandar Joshi, Danqi Chen, Y. Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2019a. Spanbert: Improving pre-training by representing and predicting spans. In Transactions of the Association for Computational Linguistics (TACL). find our card
  19. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019b. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  20. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM). find our card
  21. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR). find our card
  22. Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012a. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  23. Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012b. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  24. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017a. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  25. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017b. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  26. Qi Li, Heng Ji, and Liang Huang. 2013. Joint event extraction via structured prediction with global features. In Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics (ACL). find
  27. Dekang Lin et al. 1998. An information-theoretic definition of similarity. In Proceedings of the International Conference on Machine Learning (ICML). find
  28. Zhengzhong Liu, Jun Araki, Eduard Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). find our card
  29. 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 (ACL). find
  30. Jing Lu, Deepak Venugopal, Vibhav Gogate, and Vincent Ng. 2016. Joint inference for event coreference resolution. In Transactions of the Association for Computational Linguistics (TACL). find our card
  31. Yaojie Lu, Hongyu Lin, Jialong Tang, Xianpei Han, and Le Sun. 2020. End-to-end neural event coreference resolution. In CoRR abs/2009.08153. — [arXiv:2009.08153](https://arxiv.org/abs/2009.08153) find
  32. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the 2005 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  33. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6). find our card
  34. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39– 41. find our card
  35. Bishan Yang, Claire Cardie, and Peter Frazier. 2015. A hierarchical distance-dependent Bayesian model for event coreference resolution. In Transactions of the Association for Computational Linguistics (TACL). find
  36. Teruko Mitamura, Zhengzhong Liu, and Eduard H. Hovy. 2015. Overview of TAC-KBP 2015 event nugget track. In Proceedings of the Text Analysis Conference (TAC). find
  37. Teruko Mitamura, Zhengzhong Liu, and Eduard H. Hovy. 2016. Overview of TAC-KBP 2016 event nugget track. In Proceedings of the Text Analysis Conference (TAC). find
  38. Teruko Mitamura, Zhengzhong Liu, and Eduard H. Hovy. 2017. Events detection, coreference and sequencing: What’s next? overview of the TAC KBP 2017 event track. In Proceedings of the Text Analysis Conference (TAC). find
  39. Vincent Ng. 2010. Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  40. Thien Huu Nguyen, , Adam Meyers, and Ralph Grishman. 2016. New york university 2016 system for kbp event nugget: A deep learning approach. In Proceedings of the Text Analysis Conference (TAC). find
  41. Thien Huu Nguyen and Ralph Grishman. 2018. Graph convolutional networks with argument-aware pooling for event detection. In Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI). find
  42. Haoruo Peng, Yangqiu Song, and Dan Roth. 2016. Event detection and co-reference with minimal supervision. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  43. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael 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). find our card
  44. Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou, and Thien Huu Nguyen. 2020a. Exploiting the syntax-model consistency for neural relation extraction. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  45. Amir Pouran Ben Veyseh, Tuan Ngo Nguyen, and Thien Huu Nguyen. 2020b. Graph transformer networks with syntactic and semantic structures for event argument extraction. In Proceedings of the Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tran-2021-exploiting-document-structures-cluster-consistencies/