Abstract
Event extraction is an important task under certain profession domains. CCKS 2021 holds a communication domain event extraction benchmark and we purposed an approach with the biaffine attention mechanism to finish the task. The solution combines the state-of-the-art BERT-like base models and the biaffine attention mechanism to build a two-stage model, one stage for event trigger extraction and another for event role extraction. Besides, we apply several strategies, ensemble multi models to retrieve the final predictions. Eventually our approach performs on the competition data set well with an F1-score of 0.8033 and takes the first place on the leaderboard.
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
Sultana, S., Cavaletto, L.A., Bosu, A.: Identifying the prevalence of gender biases among the computing organizations. arXiv preprint arXiv:2107.00212 (2021)
Liu, J., et al.: Event extraction as machine reading comprehension. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (2020)
Chen, Y., et al.: Automatically labeled data generation for large scale event extraction. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (2017)
Kim, J.-T., Moldovan, D.I.: Acquisition of linguistic patterns for knowledge-based information extraction. IEEE Trans. Knowl. Data Eng. 7(5), 713–724 (1995)
Riloff, E., Shoen, J.: Automatically acquiring conceptual patterns without an annotated corpus. In: Third Workshop on Very Large Corpora (1995)
Jiang, J.: A method of obtaining event information extraction mode. Comput. Eng. (2005)
Sha, L., et al.: Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Huang, L., et al.: Zero-shot transfer learning for event extraction (2017)
Yang, S., et al.: Exploring pre-trained language models for event extraction and generation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)
Zheng, S., et al.: Doc2EDAG: an end-to-end document-level framework for Chinese financial event extraction. arXiv preprint arXiv:1904.07535 (2019)
He, R.F., Duan, S.Y.: Joint Chinese event extraction based multi-task learning. J. Softw. 30(4), 1015 (2019)
Jiang, M., et al.: A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries. J. Am. Med. Inform. Assoc. 18(5), 601–606 (2011)
Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2016)
Wang, R., Zhou, D., He, Y.: Open event extraction from online text using a generative adversarial network. arXiv preprint arXiv:1908.09246 (2019)
Zhang, J., et al.: Extracting entities and events as a single task using a transition-based neural model. In: IJCAI (2019)
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. arXiv preprint arXiv:1611.01734 (2016)
Sheng, J., et al.: A joint learning framework for the CCKS-2020 financial event extraction task. Data Intell. 3(3), 444–459 (2021)
Yu, J., Bohnet, B., Poesio, M.: Named entity recognition as dependency parsing. arXiv preprint arXiv:2005.07150 (2020)
Su, J.: Apply softmax cross-entropy loss function to multi-label classification. https://kexue.fm/archives/7359. Accessed 10 Sept 2021
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
Ji, J., He, Y., Li, J. (2022). A Biaffine Attention-Based Approach for Event Factor Extraction. 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_1
Download citation
DOI: https://doi.org/10.1007/978-981-19-0713-5_1
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)