Abstract
Few-shot learning event extraction methods gain more and more attention due to their ability to handle new event types. Current few-shot learning studies mainly focus on English event detection, which suffering from error propagation due to the identify-then-classify paradigm. And these methods could not be applied to Chinese event extraction directly, because they suffer from the Chinese word-trigger mismatch problem. In this work, we explore the Chinese event extraction with limited labeled data and reformulate it as a few-shot sequence tagging task. To this end, we propose a novel and practical few-shot syntactic enhanced projection network (SEPN), which exploits a syntactic learner to not only integrate the semantics of the characters and the words by Graph Convolution Networks, but also make the extracted feature more discriminative through a cross attention mechanism. Differing from prototypical networks which may lead to poor performance due to the prototype of each class could be closely distributed in the embedding space, SEPN learns to project embedding to space where different labels are well-separated. Furthermore, we deliberately construct an adaptive max-margin loss to obtain efficient and robust prototype representation. Numerical experiments conducted on the ACE-2005 dataset demonstrate the efficacy of the proposed few-shot Chinese event extraction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barron, J.T.: A general and adaptive robust loss function. In: Proceedings of CVPR, pp. 4331–4339 (2019)
Chen, Y., Liu, S., Zhang, X., Liu, K., Zhao, J.: Automatically labeled data generation for large scale event extraction. In: Proceedings of ACL, pp. 409–419 (2017)
Chen, Y., Xu, L., Liu, K., Zeng, D., Zhao, J.: Event extraction via dynamic multi-pooling convolutional neural networks. In: Proceedings of ACL, pp. 167–176 (2015)
Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. In: Proceedings of EMNLP, pp. 657–668 (2020)
Deng, S., Zhang, N., Kang, J., Zhang, Y., Zhang, W., Chen, H.: Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. In: Proceedings of WSDM (2019)
Gao, T., Han, X., Liu, Z., Sun, M.: Hybrid attention-based prototypical networks for noisy few-shot relation classification. In: Proceedings of the AAAI, vol. 33, pp. 6407–6414 (2019)
Hou, Y., et al.: Few-shot slot tagging with collapsed dependency transfer and label-enhanced task-adaptive projection network. In: Proceedings of ACL, pp. 1381–1393 (2020)
Huang, L., Ji, H., Cho, K., Dagan, I., Riedel, S., Voss, C.: Zero-shot transfer learning for event extraction. In: Proceedings of ACL, pp. 2160–2170 (2018)
Kingma, D., Ba, J.: Adam: A method for stochastic optimization. Computer Science (2014)
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of ACL, pp. 423–430 (2003)
Lai, V.D., Dernoncourt, F., Nguyen, T.H.: Exploiting the matching information in the support set for few shot event classification. In: Lauw, H.W., Wong, R.C.-W., Ntoulas, A., Lim, E.-P., Ng, S.-K., Pan, S.J. (eds.) PAKDD 2020, Part II. LNCS (LNAI), vol. 12085, pp. 233–245. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-47436-2_18
Lai, V.D., Nguyen, T.H., Dernoncourt, F.: Extensively matching for few-shot learning event detection. In: Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events, pp. 38–45 (2020)
Li, Q., Ji, H., Hong, Y., Li, S.: Constructing information networks using one single model. In: Proceedings of EMNLP, pp. 1846–1851 (2014)
Li, Q., Ji, H., Huang, L.: Joint event extraction via structured prediction with global features. In: Proceedings of ACL, pp. 73–82 (2013)
Linguistic Data Consortium: DEFT rich ERE annotation guidelines: Events v2.9. Technical report (2015)
Liu, X., Luo, Z., Huang, H.: Jointly multiple events extraction via attention-based graph information aggregation. In: Proceedings of EMNLP, pp. 1247–1256 (2018)
Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: Proceedings of NAACL, pp. 300–309 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Proceedings of NIPS, pp. 4077–4087 (2017)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Proceedings of NIPS, pp. 3630–3638 (2016)
Xiangyu, X., Tong, Z., Wei, Y., Jinglei, Z., Rui, X., Shikun, Z.: A hybrid character representation for Chinese event detection. In: Proceedings of IJCNN, pp. 1–8. IEEE (2019)
Yang, S., Feng, D., Qiao, L., Kan, Z., Li, D.: Exploring pre-trained language models for event extraction and generation. In: Proceedings of ACL, pp. 5284–5294 (2019)
Yoon, S.W., Seo, J., Moon, J.: Tapnet: neural network augmented with task-adaptive projection for few-shot learning. In: Proceedings of ICML, pp. 7115–7123. PMLR (2019)
Acknowledgment
We would like to thank all reviewers for their insightful comments and suggestions. This work is sponsored in part by the National Key Research & Development Program of China under Grant No. 2018YFB0204300, the Open Fund of Science and Technology on Parallel and Distributed Processing Laboratory (PDL), and the National Natural Science Foundation of China under Grant No. 62025208, 61932001, and 61806216.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, L., Qiao, L., Han, Y., Kan, Z., Gao, Y., Li, D. (2021). Syntactic Enhanced Projection Network for Few-Shot Chinese Event Extraction. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management . KSEM 2021. Lecture Notes in Computer Science(), vol 12816. Springer, Cham. https://doi.org/10.1007/978-3-030-82147-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-82147-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82146-3
Online ISBN: 978-3-030-82147-0
eBook Packages: Computer ScienceComputer Science (R0)