Elamur Research⌕
☰
home / papers / 2021 / Constrained Multi-Task Learning for Event Coreference Resolution

Constrained Multi-Task Learning for Event Coreference Resolution

Summary

Event coreference resolution asks whether two event mentions in a document describe the same real-world event. Earlier systems have two main weaknesses. Pipelines pass trigger-detection mistakes downstream. Joint-inference methods combine separately trained models under hard constraints, which can hurt when those models' outputs are noisy. Lu and Ng instead build a span-based neural network that learns event coreference together with five related tasks: trigger detection, entity coreference, anaphoricity determination, realis detection and argument extraction. Because this joint model is difficult to train, they add cross-task consistency constraints as soft penalties. For example, coreferent events should share a subtype. The penalties sit inside the pairwise coreference score, and their size grows with the degree of violation. The authors also treat entity and event coreference as one task over a common pool of mentions, a step toward unified coreference. On the KBP 2017 dataset the model reaches state-of-the-art results, beating a strong pipeline baseline. Ablations confirm that each component helps.

Key points

  • Data and setup: the model is evaluated on the KBP 2017 event coreference dataset. It is a span-based neural model, the first such model applied to event coreference, and it learns six tasks jointly.
  • Main result: the full model scores 48.0 AVG-F for event coreference, 3.1 points above the Pipeline baseline.
    • All four coreference metrics improve, with MUC up 6.6 points.
    • Trigger detection rises by 0.7 points over Pipeline.
    • Realis detection rises by 12.9 points over Jiang et al.
  • Constraint ablation: removing the soft consistency constraints lowers event coreference by 1.0 point. Realis detection is the one task that gets slightly better without them.
  • Entity coreference ablations:
    • Removing entity coreference, which also removes argument extraction, costs 2.7 points.
    • Learning entity and event coreference as separate tasks lowers event coreference by 0.8 points and entity coreference by 3 points.
  • Other ablations: dropping realis costs 1.4 points, argument extraction 0.6 points, and anaphoricity 0.5 points of event coreference AVG-F.

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

8 papers of our library cite it (of the 140673 whose bibliographies we read); 3 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 10.18653/v1/2021.naacl-main.356

@inproceedings{lu2021constrained,
  title = {{Constrained Multi-Task Learning for Event Coreference Resolution}},
  author = {Lu, Jing and Ng, Vincent},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2021},
  doi = {10.18653/v1/2021.naacl-main.356},
  url = {https://doi.org/10.18653/v1/2021.naacl-main.356}
}

References

33 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. 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
  2. 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, pages 2074–2080. find our card
  3. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the LREC Workshop on Linguistic Coreference, pages 563–566. find our card
  4. Shanshan Jiang, Yihan Li, Tianyi Qin, Qian Meng, and Bin Dong. 2017. SRCB entity discovery and linking (EDL) and event nugget systems for TAC 2017. In Proceedings of the 2017 Text Analysis Conference. find
  5. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, (8):64–77. find our card
  6. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 5803–5… find our card
  7. 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 30th AAAI Conference on Artificial Intelligence, pages 2913– 2920. find
  8. Sebastian Krause, Feiyu Xu, Hans Uszkoreit, and Dirk Weissenborn. 2016. Event linking with sentential features from convolutional neural networks. In Proceedings of the Conference of Computataional Natural Language Learning, pages 239–249. find
  9. 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, pages 17–22. find our card
  10. 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 489–50… 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, pages 2124–2133. 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 (Volume 1: Long Papers), volume 1… find our card
  13. Agata Cybulska and Piek Vossen. 2013. Semantic relations between events and their time, locations and participants for event coreference resolution. In Proceedings of the International Conference Recent Advances in Natural Language Processing, pages 156– 163. find our card
  14. 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, pages 1971–1982. find our card
  15. 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
  16. 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
  17. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 687–… find our card
  18. Tao Li, Vivek Gupta, Maitrey Mehta, and Vivek Srikumar. 2019. A logic-driven framework for consistency of neural models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 3924–393… find
  19. Zhengzhong Liu, Jun Araki, Eduard Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In Proceedings of the 9th International Conference on Language Resources and Evaluation, pages 4539–4544. find our card
  20. 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), pages 90–101. find
  21. Jing Lu and Vincent Ng. 2018. Event coreference resolution: A survey of two decades of research. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 5479–5486. find
  22. Jing Lu and Vincent Ng. 2020. Event coreference resolution with non-local information. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 653–663. find
  23. Sam Wiseman, Alexander M. Rush, Stuart Shieber, and Jason Weston. 2015. Learning anaphoricity and antecedent ranking features for coreference resolution. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural L… find our card
  24. Jing Lu, Deepak Venugopal, Vibhav Gogate, and Vincent Ng. 2016. Joint inference for event coreference resolution. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers, pages 3264–3275. find our card
  25. Yi Luan, Dave Wadden, Luheng He, Amy Shah, Mari Ostendorf, and Hannaneh Hajishirzi. 2019. A general framework for information extraction using dynamic span graphs. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tec… find our card
  26. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the Human Language Technology Conference and the 2015 Conference on Empirical Methods in Natural Language Processing, pages 25–32. find our card
  27. Katie McConky, Rakesh Nagi, Moises Sudit, and William Hughes. 2012. Improving event coreference 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
  28. Thien Huu Nguyen, Adam Meyers, and Ralph Grishman. 2016. find
  29. New York University 2016 system for KBP event nugget: A deep learning approach. In Proceedings of the 2016 Text Analysis Conference. find
  30. Haoruo Peng, Yangqi 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, pages 392–402. find our card
  31. Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand Index for coreference evaluation. Natural Language Engineering, 17(4):485– 510. find
  32. 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. find our card
  33. Haoyu Wang, Muhao Chen, Hongming Zhang, and Dan Roth. 2020. Joint constrained learning for event-event relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 696–706. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lu-2021-constrained-multi-task-learning-event/