Elamur Research⌕
☰
home / papers / 2020 / Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings

Summary

The paper addresses event coreference resolution, which means grouping event mentions that denote the same real-world event, both within a single document (WD) and across documents (CD). Earlier systems compared mentions and specific argument types separately. They depended on SRL outputs matched against entity annotations and a fixed set of argument slots, which causes error propagation and limits scalability. The authors propose EPASE, a pairwise model with two components. The first is an event-specific paraphrase module: a special [COREF] token marks the target mentions, and a BERT-style encoder judges whether two sentences paraphrase each other with respect to those particular events. The second builds argument-aware semantic embeddings by fusing semantic-role-label embeddings with token embeddings through attention, so no fixed number or type of arguments is needed. Before pairing, documents are clustered with tf-idf and K-Means. Positive pairs are oversampled and negative pairs are downsampled. On ECB+, EPASE outperforms prior systems, including the Joint model of Barhom et al. (2019) and the Chirps-enhanced approach. This shows that modeling paraphrase in context generalizes better than relying on handcrafted features.

Key points

  • Evaluated on the ECB+ corpus. On the within-document setting, EPASE reaches MUC F1 78.0 and CoNLL F1 88.3, compared with 69.7 and 84.1 for the Joint baseline (+8.3 and +4.2).
  • On the combined setting, the largest reported gains are in MUC and B³ recall, at 10.6% and 13.8% respectively.
  • Ablation (full model CoNLL F1 84.3):
    • Removing the semantic similarity component (S_sem) costs 2.2 points.
    • Removing the paraphrase component (S_para) costs 1.6 points.
    • Removing the pairwise binary features costs 0.2 points.
    • S_sem on its own still exceeds the previous SOTA by 2.7 CoNLL F1.
  • WD coreference chains in ECB+ are very short (average length 1.24). For this reason the authors treat MUC as the most informative metric for WD comparison.
  • Attention visualizations show that the [COREF] tokens collect mention and argument information from the paired sentence while largely ignoring unrelated events. Planned future work includes a stronger SRL component and an end-to-end pipeline.

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 · Machine translation

Topics: Coreference resolution · Semantic role labeling

Cited by

22 papers of our library cite it (of the 140673 whose bibliographies we read); 11 of them have a page here, 11 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.275

@inproceedings{zeng2020event,
  title = {{Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings}},
  author = {Zeng, Yutao and Jin, Xiaolong and Guan, Saiping and Guo, Jiafeng and Cheng, Xueqi},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.275},
  url = {https://doi.org/10.18653/v1/2020.coling-main.275}
}

References

24 references, 14 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, volume 1, pages 563– 566. Citeseer. 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. 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, pages 1412–1422. find our card
  4. Prafulla Kumar Choubey and Ruihong Huang. 2017. Event coreference resolution by iteratively unfolding interdependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2124–2133. 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. 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
  7. Agata Cybulska and Piek Vossen. 2015b. “bag of events” approach to event coreference resolution. supervised classification of event templates. IJCLA, page 11. find
  8. Marie-Catherine De Marneffe, Anna N Rafferty, and Christopher D Manning. 2008. Finding contradictions in text. In Proceedings of ACL-08: HLT, pages 1039–1047. find
  9. 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, Volume 1 (Long and Short Papers), pages 4171–4186. ↗
  10. Elisa Ferracane, Iain Marshall, Byron C Wallace, and Katrin Erk. 2016. Leveraging coreference to identify arms in medical abstracts: An experimental study. In Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis, pages 86–95. find
  11. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. Allennlp: A deep semantic natural language processing platform. In Proceedings of Workshop for NLP Open Source Software (NLP-OSS), pages 1–6. find our card
  12. Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415. ↗
  13. Matthew Honnibal and Ines Montani. 2017. spacy 2: Natural language understanding with bloom embeddings. convolutional neural networks and incremental parsing, 7(1). find
  14. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. find our card
  15. Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, and Dan Roth. 2018. Looking beyond the surface: A challenge set for reading comprehension over multiple sentences. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 252–262. find our card
  16. 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 489–500. Association for Computational Linguistics. Ilya Loshchilov and Frank Hutter. arXiv:1711.05101. 2017. Decoupled weight decay regularization. arXiv preprint 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. ↗ our card
  17. Yehudit Meged, Avi Caciularu, Vered Shwartz, and Ido Dagan. 2020. Paraphrasing vs coreferring: Two sides of the same coin. arXiv preprint arXiv:2004.14979. ↗ our card
  18. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational linguistics, 31(1):71–106. ↗ our card
  19. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the conference. Association for Computational Linguistics. Meeting, volume 2014, page 30. NIH Public Access. find our card
  20. Vered Shwartz, Gabriel Stanovsky, and Ido Dagan. 2017. Acquiring predicate paraphrases from news tweets. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (* SEM 2017), pages 155–160. find
  21. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008. find
  22. Marc Vilain, John D Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995. find our card
  23. Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. Constructing datasets for multi-hop reading comprehension across documents. Transactions of the Association for Computational Linguistics, 6:287–302. ↗ our card
  24. 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. ↗

↑ back to top