Abstract
Recent studies in few-shot event trigger detection from text address the task as a word sequence annotation task using prototypical networks. In this context, the classification of a word is based on the similarity of its representation to the prototypes built for each event type and for the “non-event” class (also named null class). However, the “non-event” prototype aggregates by definition a set of semantically heterogeneous words, which hurts the discrimination between trigger and non-trigger words. We address this issue by handling the detection of non-trigger words as an out-of-domain (OOD) detection problem and propose a method for dynamically setting a similarity threshold to perform this detection. Our approach increases f-score by about 10 points on average compared to the state-of-the-art methods on three datasets.
This publication was made possible by the use of the FactoryIA supercomputer, financially supported by the Île-de-France Regional Council.
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
Bronstein, O., Dagan, I., Li, Q., Ji, H., Frank, A.: Seed-based event trigger labeling: how far can event descriptions get us? In: ACL-IJCNLP, pp. 372–376 (2015). https://doi.org/10.3115/v1/P15-2061
Chen, J., Lin, H., Han, X., Sun, L.: Honey or poison? Solving the trigger curse in few-shot event detection via causal intervention. In: Proceedings of EMNLP, Punta Cana, Dominican Republic, pp. 8078–8088. Association for Computational Linguistics, November 2021. https://doi.org/10.18653/v1/2021.emnlp-main.637
Cong, X., Cui, S., Yu, B., Liu, T., Yubin, W., Wang, B.: Few-shot event detection with prototypical amortized conditional random field. In: Findings of ACL-IJCNLP, pp. 28–40, August 2021. https://doi.org/10.18653/v1/2021.findings-acl.3
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: WSDM, Houston, TX, USA, pp. 151–159, January 2020. https://doi.org/10.1145/3336191.3371796
Dror, R., Shlomov, S., Reichart, R.: Deep dominance - how to properly compare deep neural models. In: ACL, Florence, Italy, pp. 2773–2785, July 2019. https://doi.org/10.18653/v1/P19-1266
Geng, R., Li, B., Li, Y., Zhu, X., Jian, P., Sun, J.: Induction networks for few-shot text classification. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 3904–3913. Association for Computational Linguistics, November 2019. https://doi.org/10.18653/v1/D19-1403
Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, San Francisco, CA, USA, pp. 282–289 (2001)
Lai, V., Dernoncourt, F., Nguyen, T.H.: Learning prototype representations across few-shot tasks for event detection. In: EMNLP, pp. 5270–5277 (2021)
Lai, V.D., Nguyen, T.: Extending event detection to new types with learning from keywords. In: W-NUT 2019, Hong Kong, China, pp. 243–248, November 2019. https://doi.org/10.18653/v1/D19-5532
Lai, V.D., Nguyen, T.H., Dernoncourt, F.: Extensively matching for few-shot learning event detection. In: Workshop NUSE, pp. 38–45 (2020). https://doi.org/10.18653/v1/2020.nuse-1.5
Li, Q., Ji, H., Huang, L.: Joint event extraction via structured prediction with global features. In: ACL, Sofia, Bulgaria, pp. 73–82, August 2013
Liu, X., Luo, Z., Huang, H.: Jointly multiple events extraction via attention-based graph information aggregation. In: EMNLP, pp. 1247–1256 (2018). https://doi.org/10.18653/v1/D18-1156
Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: NAACL-HLT, San Diego, California, pp. 300–309 (2016). https://doi.org/10.18653/v1/N16-1034
Nguyen, T.H., Grishman, R.: Event detection and domain adaptation with convolutional neural networks. In: ACL-IJCNLP. Beijing, China, pp. 365–371 (2015). https://doi.org/10.3115/v1/P15-2060
Nguyen, T.H., Grishman, R.: Event detection and domain adaptation with convolutional neural networks. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China, pp. 365–371. Association for Computational Linguistics, July 2015. https://doi.org/10.3115/v1/P15-2060
Nguyen, T.H., Grishman, R.: Graph convolutional networks with argument-aware pooling for event detection. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Nimah, I., Fang, M., Menkovski, V., Pechenizkiy, M.: ProtoInfoMax: prototypical networks with mutual information maximization for out-of-domain detection. In: Findings of the Association for Computational Linguistics: EMNLP, pp. 1606–1617. Association for Computational Linguistics, November 2021. https://doi.org/10.18653/v1/2021.findings-emnlp.138
Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001). https://doi.org/10.1162/089976601750264965
Shen, S., Wu, T., Qi, G., Li, Y.F., Haffari, G., Bi, S.: Adaptive knowledge-enhanced Bayesian meta-learning for few-shot event detection. In: Findings of ACL-IJCNLP, pp. 2417–2429, August 2021. https://doi.org/10.18653/v1/2021.findings-acl.214
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Tan, M., et al.: Out-of-domain detection for low-resource text classification tasks. In: EMNLP-IJCNLP, pp. 3566–3572. Association for Computational Linguistics, November 2019. https://doi.org/10.18653/v1/D19-1364
Tuo, A., Besançon, R., Ferret, O., Tourille, J.: Better exploiting BERT for few-shot event detection. In: Rosso, P., Basile, V., Métais, E., Meziane, F. (eds.) NLDB 2022. LNCS, vol. 13286, pp. 291–298. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-08473-7_26
Ulmer, D.: Deep-significance: easy and better significance testing for deep neural networks, March 2021. https://doi.org/10.5281/zenodo.4638709. https://github.com/Kaleidophon/deep-significance
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Walker, C., Strassel, S., Julie Medero, K.M.: ACE 2005 multilingual training corpus (2006). https://doi.org/10.35111/mwxc-vh88
Wang, X., et al.: MAVEN: a massive general domain event detection dataset. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1652–1671. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.emnlp-main.129
Yan, H., Jin, X., Meng, X., Guo, J., Cheng, X.: Event detection with multi-order graph convolution and aggregated attention. In: EMNLP-IJCNLP, pp. 5766–5770 (2019)
Yang, Y., Katiyar, A.: Simple and effective few-shot named entity recognition with structured nearest neighbor learning. In: EMNLP, pp. 6365–6375. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.emnlp-main.516
Zhang, R., Wei, W., Mao, X.L., Fang, R., Chen, D.: HCL-TAT: a hybrid contrastive learning method for few-shot event detection with task-adaptive threshold. In: Findings of the Association for Computational Linguistics: EMNLP, pp. 1808–1819. Association for Computational Linguistics (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tuo, A., Besançon, R., Ferret, O., Tourille, J. (2023). Trigger or not Trigger: Dynamic Thresholding for Few Shot Event Detection. In: Kamps, J., et al. Advances in Information Retrieval. ECIR 2023. Lecture Notes in Computer Science, vol 13981. Springer, Cham. https://doi.org/10.1007/978-3-031-28238-6_55
Download citation
DOI: https://doi.org/10.1007/978-3-031-28238-6_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28237-9
Online ISBN: 978-3-031-28238-6
eBook Packages: Computer ScienceComputer Science (R0)