Abstract
Event coreference resolution is an important task in natural language processing. An event coreference resolution system is often divided into two tasks: Event Detection and Event Coreference Resolution. The common pipelined approaches detect the events first and then complete the event coreference resolution. However, this kind of system will bring two problems: (1) it is difficult to make rational use of event subtype information; (2) errors generated by event detection will be propagated to the event coreference component, resulting in performance degradation. In view of the above shortcomings, we propose a multitask model, which combines event subtype re-detection task and event coreference resolution task. Our model not only updates and uses the event subtype information when computing the event coreference but also can suppress error propagation by a correction mechanism. Experimental results on KBP 2016 and KBP 2017 show that our proposed system outperforms the current state-of-the-art system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Weissenborn, D., Wiese, G., Seiffe, L.: Making neural qa as simple as possible butnotsimpler. In: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 271–280 (2017)
Lin, Y., Ji, H., Huang, F., Wu, L.: A joint neural model for information extraction with global features. In: Proceedings of the ACL 2020, pp. 7999–8009 (2020)
Chen, Z., Ji, H., Haralick, R.: A pairwise event coreference model, feature impact and evaluation for event coreference resolution. In: Proceedings of the Workshop on Events in Emerging Text Types, pp. 17–22 (2009)
Liu, Z., Araki, J., Hovy, E. H., Mitamura, T.: Supervised within-document event coreference using information propagation. In: Proceedings of the LREC 2014, pp. 4539–4544 (2014)
Lu, J., Ng, V.: Joint learning for event coreference resolution. In: Proceedings of ACL 2017, pp. 90–101 (2017)
Choubey, P. K., Lee, A., Huang, R., Wang, L.: Discourse as a function of event: profiling discourse structure in news articles around the main event. In: Proceedings of ACL 2020, pp. 5374–5386 (2020)
Huang, Y. J., Lu, J., Kurohashi, S., Ng, V.: Improving event coreference resolution by learning argument compatibility from unlabeled data. In: Proceedings of NAACL 2019, pp. 785–795 (2019)
Lu, J., Ng, V.: Span-based event coreference resolution. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13489–13497 (2021)
Lu, J., Ng, V.: Event coreference resolution with non-local information. In: Proceedings of ACL-IJCNLP 2020, pp. 653–663 (2020)
Joshi, M., Chen, D., Liu, Y., et al.: SpanBERT: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguist. 8, 64–77 (2020)
Mitamura, T., Liu, Z., Hovy, E.H.: Overview of tac kbp 2015 event nugget track. In: TAC (2015)
Vilain, M.B., Burger, J.D., Aberdeen, J.S., Connolly, D., Hirschman, L.: A model-theoretic coreference scoring scheme. In: Proceedings of the MUC 1995, Columbia, Maryland, USA, 6–8 November, 1995. DBLP (1995)
Bagga, A., Baldwin, B.: Algorithms for scoring coreference chains. In: Proceedings of the LREC 1998, pp. 563–566 (1998)
Luo, X.: On coreference resolution performance metrics. In: Proceedings of Human-Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp. 25–32 (2005)
Recasens, M., Hovy, E.: BLANC: implementing the rand index for coreference evaluation. Natural language engineering, pp. 485–510 (2017)
Acknowledgments
The authors would like to thank the two anonymous reviewers for their comments on this paper. This research was supported by the National Natural Science Foundation of China (Nos. 61836007, 61772354 and 61773276.), and the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, C., Xu, S., Li, P., Zhu, Q. (2021). Multitask Model for End-to-End Event Coreference Resolution. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)