Elamur Research⌕
☰
home / papers / 2022 / Improving Event Coreference Resolution Using Document-level and Topic-level Information

Improving Event Coreference Resolution Using Document-level and Topic-level Information

Summary

Within-document event coreference resolution (ECR) groups event mentions in a text into clusters that each denote one real-world event. Earlier neural systems were constrained by input length, so they either compared mention pairs using only their sentences or encoded documents in separate chunks. This made it hard to link mentions that are far apart. Topic-level knowledge was also rarely used in deep models. The authors combine three views of each mention:

  • a Longformer encoder that reads the whole document in one pass;
  • a BERT encoder that masks the trigger and must predict the event subtype from the surrounding sentence;
  • a neural event topic generator that infers a latent topic representation.

A tensor matching scorer then compares mention pairs across these three levels, using element-wise products and a factored multi-perspective cosine similarity. On the KBP 2017 dataset, the model beats previous SOTA baselines. It needs no extra inputs such as parses, entity chains or semantic roles. The authors present it as the first ECR approach to encode an entire document at once.

Key points

  • The model has four parts: Global Mention Encoder (Longformer), Local Mention Encoder (BERT with trigger masking and a subtype-classification loss), Event Topic Generator, and Tensor Matching Scorer. Code is released on GitHub (jsksxs360/event-coref-emnlp2022).
  • Adding topic information helps long coreference chains (≥10 mentions). With ETG, event-pair F1 on these chains rises from 51.4 to 52.1. The trade-off is slightly worse singleton accuracy (48.7 → 47.8) and slightly lower F1 on short chains.
  • In the matching ablation, product plus cosine matching reached an average F of 51.2, compared with 45.4 for plain concatenation (+5.8). Adding absolute difference, or a contrastive loss, did not improve results further.
  • The authors note two limitations. The system is a pipeline, so trigger-detection errors propagate, and their attempt at a joint version performed noticeably worse. Running both Longformer and BERT also requires a lot of GPU memory.

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

5 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 4 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.emnlp-main.454

@inproceedings{xu2022improving,
  title = {{Improving Event Coreference Resolution Using Document-level and Topic-level Information}},
  author = {Xu, Sheng and Li, Peifeng and Zhu, Qiaoming},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  year = {2022},
  doi = {10.18653/v1/2022.emnlp-main.454},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.454}
}

References

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

  1. 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, pages 563–566. find our card
  2. 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, pages 4179–4189. find our card
  3. Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150. find
  4. Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, and Jun Zhao. 2021. Uncertain local-to-global networks for document-level event factuality identification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2636–2645. find
  5. 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 Thirtieth AAAI Conference on Artificial Intelligence, pages 2913–2920. find
  6. 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, ACL-IJCNLP 2009, pages 54–57. find our card
  7. Zheng Chen, Heng Ji, and Robert M 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
  8. 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
  9. 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, pages 485–495. find our card
  10. 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, pages 5374–5386. find
  11. 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
  12. Alexis Conneau, Douwe Kiela, Holger Schwenk, Loic Barrault, and Antoine Bordes. 2017. Supervised learning of universal sentence representations from natural language inference data. arXiv preprint arXiv:1705.02364. find our card
  13. Agata Cybulska and Piek Vossen. 2015. "bag of events" approach to event coreference resolution. supervised classification of event templates. International Journal of Computational Linguistics and Applications, 6(2):11–27. find
  14. 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
  15. Samuel Kriman and Heng Ji. 2021. Joint detection and coreference resolution of entities and events with document-level context aggregation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Proce… find
  16. Tuan Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, and Walter Chang. 2021. A context-dependent gated module for incorporating symbolic semantics into event coreference resolution. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational… find our card
  17. 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, pages 489–500. find our card
  18. I-Ta Lee, Maria Leonor Pacheco, and Dan Goldwasser. 2020. Weakly-supervised modeling of contextualized event embedding for discourse relations. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4962–4972. find our card
  19. Wei Li, Lei He, and Hai Zhuge. 2016. Abstractive news summarization based on event semantic link network. In Proceedings of the 26th International Conference on Computational Linguistics, pages 236–246. find
  20. Jian Liu, Yubo Chen, Kang Liu, Yantao Jia, and Zhicheng Sheng. 2020a. How does context matter? on the robustness of event detection with context-selective mask generalization. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2523–2532. find
  21. Xin Liu, Jiefu Ou, Yangqiu Song, and Xin Jiang. 2020b. On the importance of word and sentence representation learning in implicit discourse relation classification. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pages 3830–3836. find
  22. 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 Seventh Joint Conference on Lexical and Computational Semantics, pages 1–10. find our card
  23. Zhengzhong Liu, Jun Araki, Eduard H 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
  24. Diederik P Kingma and Max Welling. 2013. Autoencoding variational bayes. arXiv preprint arXiv:1312.6114. find our card
  25. 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, pages 90–101. find
  26. Sebastian Krause, Feiyu Xu, Hans Uszkoreit, and Dirk Weissenborn. 2016. Event linking with sentential features from convolutional neural networks. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pages 239–249. find
  27. 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
  28. 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
  29. Jing Lu and Vincent Ng. 2021a. Span-based event coreference resolution. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 13489– 13497. find
  30. Jing Lu and Vincent Ng. 2021b. Constrained multi-task learning for event coreference resolution. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4504–4514. find our card
  31. Jing Lu and Vincent Ng. 2021c. Conundrums in event coreference resolution: Making sense of the state of the art. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1368–1380. find our card
  32. 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, pages 3264–3275. find our card
  33. Yaojie Lu, Hongyu Lin, Jialong Tang, Xianpei Han, and Le Sun. 2022. End-to-end neural event coreference resolution. Artificial Intelligence, 303:103632. find
  34. 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
  35. Teruko Mitamura, Zhengzhong Liu, and Eduard H Hovy. 2015. Overview of TAC KBP 2015 event nugget track. In Proceedings of the Text Analysis Conference. find
  36. Teruko Mitamura, Zhengzhong Liu, and Eduard H Hovy. 2016. Overview of tac-kbp 2016 event nugget track. In Proceedings of the Text Analysis Conference. find
  37. Teruko Mitamura, Zhengzhong Liu, and Eduard H Hovy. 2017. Overview of tac kbp 2015 event nugget track. In Events Detection, Coreference and Sequencing: What’s Next? Overview of the TAC KBP 2017 Event Track. find
  38. 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. find
  39. Wenzhe Pei, Tao Ge, and Baobao Chang. 2014. Max-margin tensor neural network for chinese word segmentation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 293–303. find
  40. 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, pages 392–402. find our card
  41. Duy Phung, Tuan Ngo Nguyen, and Thien Huu Nguyen. 2021. Hierarchical graph convolutional networks for jointly resolving cross-document coreference of entity and event mentions. In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing, pages 32–41. find
  42. Marta Recasens and Eduard Hovy. 2011. Blanc: Implementing the rand index for coreference evaluation. Natural language engineering, 17(4):485–510. find
  43. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084. find
  44. Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of the 31st International Conference on Machine Learning, pages 1278–1286. find our card
  45. Jianlin Su. 2021. Variational autoencoders (7): Vae on a sphere (vmf-vae). find
  46. Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, and Jun Xie. 2020. Improving event detection via open-domain trigger knowledge. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 5887–5897. find
  47. Hieu Minh Tran, Duy Phung, and Thien Huu Nguyen. 2021. Exploiting document structures and cluster consistencies for event coreference resolution. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language… find our card
  48. Marc Vilain, John D Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Message Understanding Conference. find our card
  49. Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, and Guodong Zhou. 2019. Topic tensor network for implicit discourse relation recognition in chinese. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 608–618. find our card
  50. Bishan Yang, Claire Cardie, and Peter Frazier. 2015. A hierarchical distance-dependent bayesian model for event coreference resolution. Transactions of the Association for Computational Linguistics, 3:517– 528. find
  51. Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, and Xueqi Cheng. 2020. Event coreference resolution with their paraphrases and argument-aware embeddings. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3084–3094. find our card

↑ back to top