Elamur Research⌕
☰
home / papers / 2023 / Cross-Document Event Coreference Resolution on Discourse Structure

Cross-Document Event Coreference Resolution on Discourse Structure

Summary

Cross-document event coreference resolution (CD-ECR) groups event mentions from several documents that describe the same real-world event. Most earlier systems compare mention pairs using only nearby context, so they struggle when the two mentions are far apart or appear in different documents. Chen et al. add global signals from discourse structure. A DRS constructor (segmentor plus parser) converts text into a discourse tree whose leaves are EDUs. For each mention pair, the model uses the tree node where their paths meet (LCP) and the shortest path between them (DT-SDP). A Bi-LSTM encodes the rhetorical and nuclearity labels along that path. These global features are combined with local trigger and EDU embeddings from RoBERTa LARGE, and an MLP then scores coreference. For pairs that span two documents, the authors build a joint cross-document tree. Its best variant keeps the event sentences and compresses the surrounding text before concatenating the documents. On ECB+, the system beats several baselines and is competitive with the state of the art. This suggests that discourse-level links help connect distant mentions.

Key points

  • Evaluated on the ECB+ corpus using gold (annotated) event mentions; event detection is outside the scope of the work.
  • Local representation: documents longer than 512 word-piece tokens are split at whole-EDU boundaries rather than at a fixed token cut. Trigger-pair and EDU-pair vectors take the form [a, b, a∘b].
  • Three cross-document tree strategies are compared: ES-only, Full-doc and ES-comp. ES-comp works best, while Full-doc adds noise and ES-only can drop useful rhetorical nodes.
  • A case study (Matt Smith cast as the Doctor) shows a DT-SDP containing NS-Elaborate carrying the shared argument "Smith" between the mentions "winning" and "chosen".
  • The authors claim to be the first to apply cross-document discourse trees to CD-ECR. They note slow DRS constructor inference and an improvable tree-building strategy as limitations.

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: Discourse analysis · Coreference resolution

Cited by

8 papers of our library cite it (of the 140673 whose bibliographies we read); 2 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/v1/2023.emnlp-main.294

@inproceedings{chen2023cross,
  title = {{Cross-Document Event Coreference Resolution on Discourse Structure}},
  author = {Chen, Xinyu and Xu, Sheng and Li, Peifeng and Zhu, Qiaoming},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  doi = {10.18653/v1/2023.emnlp-main.294},
  url = {https://doi.org/10.18653/v1/2023.emnlp-main.294}
}

References

49 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jun Araki and Teruko Mitamura. 2015. Joint event trigger identification and event coreference resolution with structured perceptron. In EMNLP, pages 2074– 2080. find our card
  2. Amit Bagga. 1998. Evaluation of coreferences and coreference resolution systems. In LREC, pages 563– 572. find
  3. 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 ACL, pages 4179– 4189. find our card
  4. Cosmin Adrian Bejan and Sanda M. Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In ACL, pages 1412–1422. find our card
  5. Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, and Ido Dagan. 2021. CDLM: cross-document language modeling. In EMNLP (Findings), pages 2648–2662. find
  6. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2021. Cross-document coreference resolution over predicted mentions. In ACL/IJCNLP (Findings), pages 5100–5107. 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 AAAI, pages 2913–2920. find
  8. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In EMNLP, pages 1971–1982. find our card
  9. Jie Fang and Peifeng Li. 2020. Data augmentation with reinforcement learning for document-level event coreference resolution. In NLPCC, pages 751–763. find
  10. Jie Fang, Peifeng Li, and Guodong Zhou. 2018. Employing multiple decomposable attention networks to resolve event coreference. In NLPCC, pages 246– 256. find
  11. William Held, Dan Iter, and Dan Jurafsky. 2021. Focus on what matters: Applying discourse coherence theory to cross document coreference. In EMNLP, pages 1406–1417. find our card
  12. Yin Jou Huang, Jing Lu, Sadao Kurohashi, and Vincent Ng. 2019. Improving event coreference resolution by learning argument compatibility from unlabeled data. In NAACL-HLT, pages 785–795. find
  13. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel S. Weld. 2019. BERT for coreference resolution: Baselines and analysis. In EMNLP/IJCNLP, pages 5802–5807. find our card
  14. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. In *SEM@NAACL-HLT, pages 1–10. find our card
  15. Zheng Chen and Heng Ji. 2009. Graph-based event coreference resolution. In ACL, pages 54–57. find our card
  16. Sebastian Krause, Feiyu Xu, Hans Uszkoreit, and Dirk Weissenborn. 2016. Event linking with sentential features from convolutional neural networks. In CoNLL, pages 239–249. find
  17. Fei Cheng and Yusuke Miyao. 2017. Classifying temporal relations by bidirectional LSTM over dependency paths. In ACL, pages 1–6. find
  18. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In EMNLP, pages 188–197. find our card
  19. Haoyi Cheng, Peifeng Li, and Qiaoming Zhu. 2019. Employing gated attention and multi-similarities to resolve document-level chinese event coreference. In IALP, pages 296–301. find
  20. Shulin Liu, Yubo Chen, Kang Liu, and Jun Zhao. 2017. Exploiting argument information to improve event detection via supervised attention mechanisms. In ACL, pages 1789–1798. find
  21. Prafulla Kumar Choubey and Ruihong Huang. 2018. Improving event coreference resolution by modeling correlations between event coreference chains and document topic structures. In ACL, pages 485–495. find our card
  22. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692. find
  23. 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 ACL, pages 5374–5386. find
  24. 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
  25. Agata Cybulska and Piek Vossen. 2015. Translating granularity of event slots into features for event coreference resolution. In EVENTS@HLP-NAACL, pages 1–10. find our card
  26. 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
  27. Zhengzhong Liu, Teruko Mitamura, and Eduard H. Hovy. 2018. Graph based decoding for event sequencing and coreference resolution. In COLING, pages 3645–3657. find
  28. Jing Lu and Vincent Ng. 2017. Joint learning for event coreference resolution. In ACL, pages 90–101. find
  29. Jing Lu and Vincent Ng. 2021. Span-based event coreference resolution. In AAAI, pages 13489–13497. find
  30. Jing Lu, Deepak Venugopal, Vibhav Gogate, and Vincent Ng. 2016. Joint inference for event coreference resolution. In COLING, pages 3264–3275. find our card
  31. Yaojie Lu, Hongyu Lin, Jialong Tang, Xianpei Han, and Le Sun. 2020. End-to-end neural event coreference resolution. CoRR, abs/2009.08153. — [arXiv:2009.08153](https://arxiv.org/abs/2009.08153) find
  32. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In HLT/EMNLP, pages 25–32. find our card
  33. William C Mann and Sandra A Thompson. 1998. Rhetorical structure theory: Toward a functional theory of text organization. Text - Interdisciplinary Journal for the Study of Discourse, 8(3):243–281. find
  34. Hu Xu, Bing Liu, Lei Shu, and Philip S. Yu. 2019. BERT post-training for review reading comprehension and aspect-based sentiment analysis. In ACL, pages 2324–2335. find our card
  35. Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng, and Zhi Jin. 2015. Classifying relations via long short term memory networks along shortest dependency paths. In EMNLP, pages 1785–1794. find
  36. Bishan Yang, Claire Cardie, and Peter I. Frazier. 2015. A hierarchical distance-dependent bayesian model for event coreference resolution. Trans. Assoc. Comput. Linguistics, 3:517–528. find
  37. Xiaodong Yu, Wenpeng Yin, and Dan Roth. 2022. Pairwise representation learning for event coreference. In *SEM@NAACL-HLT, pages 69–78. find our card
  38. Vincent Ng. 2010. Supervised noun phrase coreference research: The first fifteen years. In ACL, pages 1396– 1411. find our card
  39. Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, and Xueqi Cheng. 2020. Event coreference resolution with their paraphrases and argument-aware embeddings. In COLING, pages 3084–3094. 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 TAC. NIST. find
  41. Longyin Zhang, Fang Kong, and Guodong Zhou. 2021. Adversarial learning for discourse rhetorical structure parsing. In ACL/IJCNLP, pages 3946–3957. find our card
  42. Cristina Nicolae and Gabriel Nicolae. 2006. BESTCUT: A graph algorithm for coreference resolution. In EMNLP, pages 275–283. find our card
  43. Haoruo Peng, Yangqiu Song, and Dan Roth. 2016. Event detection and co-reference with minimal supervision. In EMNLP, pages 392–402. find our card
  44. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67. find
  45. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nate Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher D. Manning. 2010. A multi-pass sieve for coreference resolution. In EMNLP, pages 492–501. find our card
  46. Satyan Sangeetha and Michael Arock. 2012. Event coreference resolution using mincut based graph clustering. International Journal of Computing and Information Sciences, pages 253–260. find
  47. Marc B. Vilain, John D. Burger, John S. Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In MUC, pages 45–52. find our card
  48. Charles L. Wayne. 1998. Topic detection & tracking: a case study in corpues creation & evaluation methodologies. In LREC, pages 111–116. find
  49. Dirk Weissenborn, Georg Wiese, and Laura Seiffe. 2017. Making neural QA as simple as possible but not simpler. In CoNLL, pages 271–280. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chen-2023-cross-document-event-coreference-resolution/