Employing Multiple Decomposable Attention Networks to Resolve Event Coreference

  • Jie Fang
  • Peifeng LiEmail author
  • Guodong Zhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)


Event coreference resolution is a challenging NLP task due to this task needs to understand the semantics of events. Different with most previous studies used probability-based or graph-based models, this paper introduces a novel neural network, MDAN (Multiple Decomposable Attention Networks), to resolve document-level event coreference from different views, i.e., event mention, event arguments and trigger context. Moreover, it applies a document-level global inference mechanism to further resolve the coreference chains. The experimental results on two popular datasets ACE and TAC-KBP illustrate that our model outperforms the two state-of-the-art baselines.


Event coreference Decomposable Attention Network Global inference 



The authors would like to thank three anonymous reviewers for their comments on this paper. This research was supported by the National Natural Science Foundation of China under Grant Nos. 61772354, 61773276 and 61472265, and was also supported by the Strategic Pioneer Research Projects of Defense Science and Technology under Grant No. 17-ZLXDXX-02-06-02-04.


  1. 1.
    Allan, J., Carbonell, J.G., Doddington, G., Yamron, J., Yang, Y.: Topic detection and tracking pilot study: final report. In: Proceedings of the DARPA Broadcast News Transcription and Understanding Workshop, pp. 194–218 (1998)Google Scholar
  2. 2.
    Li, P., Zhu, Q., Zhou, G.: Argument inference from relevant event mentions in chinese argument extraction. In: Proceedings of ACL 2013, pp. 1477–1487 (2013)Google Scholar
  3. 3.
    Narayanan, S., Harabagiu, S.: Question answering based on semantic structures. In: Proceedings of COLING 2004, pp. 693–702 (2016)Google Scholar
  4. 4.
    Parikh, A.P., Tackstrom, O., Uszkoreit, J.: A decomposable attention model for natural language inference. In: Proceedings of EMNLP 2016, pp. 2249–2255 (2016)Google Scholar
  5. 5.
    Cybulska, A., Vossen, P.: Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In: Proceedings of LREC 2014, pp. 4545–4552 (2014)Google Scholar
  6. 6.
    Bejan, C.A., Harabagiu, S.: Unsupervised event coreference resolution. Comput. Linguist. 40(2), 311–347 (2014)CrossRefGoogle Scholar
  7. 7.
    Ng, V., Cardie, C.: Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution. In: Proceedings of COLING 2002, pp. 1–7 (2002)Google Scholar
  8. 8.
    Chen, Z., Ji, H.: Graph-based event coreference resolution. In: Proceedings of TextGraphs 4, pp. 54–57 (2009)Google Scholar
  9. 9.
    Liu, Z., Araki, J., Hovy, E., Mitamura, T.: Supervised within-document event coreference using information propagation. In: LREC 2014, pp. 4539–4544 (2014)Google Scholar
  10. 10.
    Lu, J., Ng, V.: Joint learning for event coreference resolution. In: Proceedings of ACL 2017, pp. 90–101 (2017)Google Scholar
  11. 11.
    Krause, S., Xu, F., Uszkoreit, H., Weissenborn, D.: Event linking with sentential features from convolutional neural networks. In: Proceedings of CoNLL 2016, pp. 239–249 (2016)Google Scholar
  12. 12.
    Haghighi, A., Klein, D.: Simple coreference resolution with rich syntactic and semantic features. In: Proceedings of EMNLP 2009, pp. 1152–1161 (2009)Google Scholar
  13. 13.
    Vilain, M., Burger, J., Aberdeen, J., Connolly, D., Hirschman, L.: A model-theoretic coreference scoring scheme. In: Proceedings of MUC-6, pp. 45–52 (1995)Google Scholar
  14. 14.
    Mitamura, T., Liu, Z., Hovy, E.: Overview of TAC-KBP 2015 event nugget track. In: Proceedings of TAC 2015 (2015)Google Scholar
  15. 15.
    Lu, J., Ng, V.: UTD’s event nugget detection and coreference system at KBP 2016. In: Proceedings of TAC 2016 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologySoochow UniversitySuzhouChina

Personalised recommendations