Abstract
The existing event coreference resolution models is hard to identify the coreferent relation between non-verb-triggered event mention and verb-triggered event mention, due to their different expressions. Motivated by the recent successful application of the sentence rewriting models on information extraction and the fact that event triggers and arguments are beneficial for event coreference resolution, we employ the sentence rewriting mechanism to boost event coreference resolution. First, we rewrite the sentences containing non-verbs-triggered event mentions and convert them to verb-triggered by the fine-tuning pre-training model and few-shot learning. Then, we utilize semantic roles labeling to extract the event arguments from the original sentences with verb-triggered event mention and the rewritten sentences. Finally, we feed the event sentences, the triggers, and the arguments to BERT with a multi-head attention mechanism to resolve those coreferent events. Experimental results on both the KBP 2016 and KBP 2017 datasets show that our proposed model outperforms the state-of-the-art baseline.
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
Gardner, M., Grus, J., Neumann, M.: AllenNLP: a deep semantic natural language processing platform. In: Proceedings of the ACL Workshop for Natural Language Processing Open Source Software, pp. 1–6 (2017)
Bao, G., Zhang, Y.: Contextualized rewriting for text summarization. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (2021)
Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, pp. 74–81 (2004)
Walker, C., Strassel, S., Medero, J., Maeda, K.: ACE2005 multilingual training corpus. Progress of Theoretical Physics Supplement (2006)
Mitamura, T., Liu, Z., Hovy, E.: Overview of TAC KBP 2015 event nugget track. In: Proceedings of the TAC (2015)
Ahn, D.: The stages of event extraction. In: Proceedings of ACL 2006, pp. 1–8 (2006)
Bejan, C.A., Harabagiu, S.M.: Unsupervised event coreference resolution with rich linguistic features. In: Proceedings of ACL 2010, pp. 1412–1422 (2010)
Ng, V., Claire, C.: Identifying anaphoric and nonanaphoric noun phrases to improve coreference resolution. In: Proceedings of ACL 2002, pp. 1–7 (2002)
Peng, H., Song, Y., Dan, R.: Event detection and coreference with minimal supervision. In: Proceedings of EMNLP 2016, pp. 192–402 (2016)
Lu, J., Ng, V.: Joint learning for event coreference resolution. In: Proceedings of ACL 2017, pp. 90–101 (2017)
Huang, Y.J., Lu, J., Kurohashi, S., Ng, V.: Improving event coreference resolution by learning argument compatibility from unlabeled data. In: Proceedings of ACL 2019, pp. 785–795 (2019)
Fang, J., Li, P.: Data augmentation with reinforcement learning for document-level event coreference resolution. In: Zhu, X., Zhang, M., Hong, Yu., He, R. (eds.) NLPCC 2020. LNCS (LNAI), vol. 12430, pp. 751–763. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60450-9_59
Lu, J., Ng, V.: Span-based event coreference resolution. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (2021)
Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the Ninth International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)
Chen, Z., Eavani, H., Chen, W., Liu, Y., Wang, Y.: Few-Shot NLG with pre-trained language model. In: Proceedings of ACL 2020, pp. 183–190 (2020)
Lin, T., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Patt. Anal. Mach. Intell. 42, 2999–3007 (2017)
Vilain, M.B., Burger, J.D., Aberdeen, J.S., Connolly, D., Hirschman, L.: A model-theoretic coreference scoring scheme. In: Proceeding of the 6th MUC (1995)
Bagga, A., Baldwin, B.: Algorithms for scoring coreference chains. In: Proceedings of LREC 1998, pp. 563–566 (1998)
Recasens, M., Hovy, E.: BLANC: Implementing the rand index for coreference evaluation. Nat. Lang. Eng. 17, 485–510 (2017)
Luo, X.: On coreference resolution performance metrics. In: Proceedings of EMNLP 2005, pp. 25–32 (2005)
Yang, S., Feng, D., Qiao, L., Kan, Z., Li, D.: Exploring pre-trained language models for event extraction and generation. In: Proceedings of ACL 2019, pp. 5284–5294 (2019)
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. 61772354, 61836007 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
Chen, X., Xu, S., Li, P., Zhu, Q. (2021). Sentence Rewriting with Few-Shot Learning for Document-Level Event Coreference Resolution. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13108. Springer, Cham. https://doi.org/10.1007/978-3-030-92185-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-92185-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92184-2
Online ISBN: 978-3-030-92185-9
eBook Packages: Computer ScienceComputer Science (R0)