Abstract
There are many different expressions for the same event. The goal of event co-reference resolution is to build a calculation model for the similarity of event expressions to achieve the unity of data. Based on the Roberta pre-trained model, aiming at the problem of unbalanced distribution of difficult and easy cases in data, the effectiveness of various methods to enhance the generalization ability of the model is explored, including different data input methods, data enhancement, different loss functions, adversarial learning, contrastive learning. The best data input and model training methods are finally selected. On the CCKS2021 event co-reference resolution task for communication field, the f1 value of single model reaches 0.80 in test dataset 1 and 0.89 in test dataset 2.
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
Similar content being viewed by others
References
Ahn, D.: The stages of event extraction. In: Proceedings of the Workshop of the ACL on Annotating and Reasoning about Time and Events, pp. 1–8 (2006)
Wang, J., Song, X., Du, H.: Research on synonymous expression pattern extraction for coreference event recognition. J. China Soc. Sci. Tech. Inf. 39(03), 297–307 (2020)
Chen, B., Su, J., Pan, S.J., Tan, C.L.: A unified event coreference resolution by integrating multiple resolvers. In: Proceedings of the 5th International Joint Conference on Natural Language Processing, pp. 102–110 (2011)
Lee, H., Recasens, M., Chang, A., Surdeanu, M., Jurafsky, D.: Joint entity and event coreference resolution across documents. In: Proceedings of Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 489–500 (2012)
Liu, Z., Araki, J., Hovy, E., Mitamura, T.: Supervised within-document event coreference using information propagation. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation, pp. 4539–4544 (2014)
Zeng, D., Liu, K., Lai, S., Zhou, G., Zhao, J.: Relation classification via convolutional deep neural network. In: COLING, pp. 2335–2344. The Association for Computational Linguistics (2014)
Krause, S., Xu, F., Uszkoreit, H., Weissenborn, D.: Event linking with sentential features from convolutional neural networks. In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL), pp. 239–249 (2016)
dos Santos, C.N., Xiang, B., Zhou, B.: Classifying relations by ranking with convolutional neural networks. In: ACL, vol. 1, pp. 626–634. The Association for Computational Linguistic (2015)
Jie, F., Li, P., Zhu, Q.: An event reference resolution method based on multi-attention mechanism. Comput. Sci. 46(8), 277–281 (2019)
Eunmin, C.H., Peifeng, L.: Chinese event coreference resolution method based on structured representation. J. Chin. Inf. Process. 33(12), 19–27 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yu, X., Bai, X., Liao, S., Cui, H. (2022). Strategies for Enhancing Generalization Ability of Communication Event Co-reference Resolution. In: Qin, B., Wang, H., Liu, M., Zhang, J. (eds) CCKS 2021 - Evaluation Track. CCKS 2021. Communications in Computer and Information Science, vol 1553. Springer, Singapore. https://doi.org/10.1007/978-981-19-0713-5_16
Download citation
DOI: https://doi.org/10.1007/978-981-19-0713-5_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0712-8
Online ISBN: 978-981-19-0713-5
eBook Packages: Computer ScienceComputer Science (R0)