A Class-Incremental Learning Method for Interactive Event Detection via Interaction, Contrast and Distillation
Source abstract
Abstract
Event detection is a crucial task in information extraction. Existing research primarily focuses on machine automatic detection tasks, which often perform poorly in certain practical applications. To address this, an interactive event-detection mode of “machine recommendation-human review–machine incremental learning” was proposed. In this mode, we study a few-shot continual class-incremental learning scenario, where the challenge is to learn new-class events with limited samples while preserving memory of old class events. To tackle these challenges, we propose a class-incremental learning method for interactive event detection via Interaction, Contrast and Distillation (ICD). We design a replay strategy based on representative and confusable samples to retain the most valuable samples under limited conditions; we introduce semantic-boundary-smoothness contrastive learning for effective learning of new-class events with few samples; and we employ hierarchical distillation to mitigate catastrophic forgetting. These methods complement each other and show strong performance. Experimental results demonstrate that, in the 5-shot 5-round class incremental-learning settings on two Chinese event-detection datasets ACE and DuEE, our method achieves final recall rates of 71.48% and 90.39%, respectively, improving by 6.86% and 3.90% over the best baseline methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Anomaly Detection Techniques and Applications · Network Security and Intrusion Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China
Funding
National Natural Science Foundation of China · National University of Defense Technology · Science and Technology on Information Systems Engineering Laboratory
References (37)
Show source-provided references
1. Duan, J., and Zhang, X. (2024). Chinese Event Trigger Recommendation Model for High-Accuracy Applications. Preprints, 2024091129.10.20944/preprints202409.1129.v1 ↗
2. Cao, P., Chen, Y., Zhao, J., and Wang, T. (2020, January 16–20). Incremental Event Detection via Knowledge Consolidation Networks. Proceedings of the Conference on Empirical Methods in Natural Language Processing 2020, Online.10.18653/v1/2020.emnlp-main.52 ↗
3. Yu, P., Ji, H., and Natarajan, P. (2021, January 7–11). Lifelong Event Detection with Knowledge Transfer. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online.10.18653/v1/2021.emnlp-main.428 ↗
4. Liu, M., Chang, S., and Huang, L. (2022, January 12–17). Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea.
5. Liu, M., and Huang, L. (2023). Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction. arXiv.10.18653/v1/2023.findings-acl.141 ↗
6. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv.
7. Chen, Y., Xu, L., Liu, K., Zeng, D., and Zhao, J. (2015, January 26–31). Event Extraction Via Dynamic Multi-Pooling Convolutional Neural Networks. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China.10.3115/v1/P15-1017 ↗
8. Wang, S., Yu, M., Chang, S., Sun, L., and Huang, L. (2022). Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding. Findings of the Association for Computational Linguistics: ACL 2022, Association for Computational Linguistics.10.18653/v1/2022.findings-acl.16 ↗
9. Wang, S., Yu, M., and Huang, L. (2022). The Art of Prompting: Event Detection based on Type Specific Prompts. arXiv.10.18653/v1/2023.acl-short.111 ↗
10. Guan, Y., Chen, J., Lecue, F., Pan, J., Li, J., and Li, R. (2023). Trigger-Argument based Explanation for Event Detection. Findings of the Association for Computational Linguistics: ACL, Association for Computational Linguistics.10.18653/v1/2023.findings-acl.312 ↗
11. Nateras, L.G., Dernoncourt, F., and Nguyen, T. (2023, January 9–14). Hybrid Knowledge Transfer for Improved Cross-Lingual Event Detection via Hierarchical Sample Selection. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, USA.
12. Yue, Z., Zeng, H., Lan, M., Ji, H., and Wang, D. (2023). Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning. arXiv.10.18653/v1/2023.acl-long.440 ↗
13. Liu, J., Sui, D., Liu, K., Liu, H., and Zhao, Z. (2023, January 9–14). Learning with Partial Annotations for Event Detection. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, USA.10.18653/v1/2023.acl-long.30 ↗
14. Xu, C., Zeng, Z., Duan, J., Qi, Q., and Zhang, X. (2023, January 17–19). Extracting Events Using Spans Enhanced with Trigger-Argument Interaction. Proceedings of the International Conference on Intelligent Systems and Knowledge Engineering, Fuzhou, China.10.1109/ISKE60036.2023.10480953 ↗
15. Nguyen, T.H., Cho, K., and Grishman, R. (2016). Joint Event Extraction via Recurrent Neural Networks, Association for Computational Linguistics.10.18653/v1/N16-1034 ↗
16. Wei, Y., Liu, S., Lv, J., Xi, X., Yan, H., Ye, W., Mo, T., Yang, F., and Wan, G. (2022, January 12–17). DESED: Dialogue-based Explanation for Sentence-level Event Detection. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea.
17. Zheng, S., Wang, F., Bao, H., Hao, Y., Zhou, P., and Xu, B. (2017). Joint Extraction Of Entities And Relations Based on a Novel Tagging Scheme. arXiv.10.18653/v1/P17-1113 ↗
18. Tian, C., Zhao, Y., and Ren, L. (2019, January 25–28). A Chinese Event Relation Extraction Model Based on BERT. Proceedings of the 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD), Chengdu, China.10.1109/ICAIBD.2019.8837002 ↗
19. Cao, H., Li, J., Su, F., Li, F., Fei, H., Wu, S., Li, B., Zhao, L., and Ji, D. (2022). OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction. arXiv.
20. Li, H., Mo, T., Fan, H., Wang, J., Wang, J., Zhang, F., and Li, W. (2022, January 12–17). KiPT: Knowledge-injected Prompt Tuning for Event Detection. Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea.
21. Yang, S., Feng, D., Qiao, L., Kan, Z., and Li, D. (2019). Exploring Pre-Trained Language Models for Event Extraction and Generation, Association for Computational Linguistics.10.18653/v1/P19-1522 ↗
22. Xinya, D., and Claire, C. (2020). Event Extraction by Answering (Almost) Natural Questions, Association for Computational Linguistics.
23. Yunmo, C., Tongfei, C., Seth, E., and Benjamin, V.D. (2020). Reading the Manual: Event Extraction as Definition Comprehension. arXiv.
24. Li, F., Peng, W., Chen, Y., Wang, Q., Pan, L., Lyu, Y., and Zhu, Y. (2020). Event Extraction as Multi-Turn Question Answering, Association for Computational Linguistics.10.18653/v1/2020.findings-emnlp.73 ↗
25. Wan, X., Mao, Y., and Qi, R. (2023). Chinese Event Detection without Triggers Based on Dual Attention. Appl. Sci., 13.10.3390/app13074523 ↗
26. Yan, Y., Liu, Z., Gao, F., and Gu, J. (2023). Type Hierarchy Enhanced Event Detection without Triggers. Appl. Sci., 13.10.3390/app13042296 ↗
27. Learning Without Forgetting10.1109/TPAMI.2017.2773081 ↗
28. D’Autume, C.D.M., Ruder, S., Kong, L., and Yogatama, D. (2019, January 8–14). Episodic Memory In Lifelong Language Learning. Proceedings of the Advances in Neural Information Processing Systems 32 (NIPS 2019), Vancouver, BC, Canada.
29. Rebuffi, S.-A., Kolesnikov, A., Sperl, G., and Lampert, C.H. (2016, January 27–30). Icarl: Incremental Classifier and Representation Learning. Proceedings of the Computer Vision and Pattern Recognition 2016, Las Vegas, NV, USA.10.1109/CVPR.2017.587 ↗
30. Lopez-Paz, D., and Ranzato, M.A. (2017, January 4–9). Gradient Episodic Memory For Continual Learning. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA.
31. Mallya, A., and Lazebnik, S. (2018, January 18–23). PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00810 ↗
32. Serrà, J., Surís, D., Miron, M., and Karatzoglou, A. (2018, January 10–15). Overcoming catastrophic forgetting with hard attention to the task. Proceedings of the International Conference on Machine Learning (ICML 2018), Stockholm, Sweden.
33. Cao, Y., Peng, H., Wu, J., Dou, Y., Li, J., and Yu, P.S. (2021, January 19–23). Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs. Proceedings of the WWW ’21: The Web Conference 2021, Ljubljana, Slovenia.10.1145/3442381.3449834 ↗
34. HEFT: A History-Enhanced Feature Transfer framework for incremental event detection10.1016/j.knosys.2022.109601 ↗
35. Luo, R., Xu, J., Zhang, Y., Ren, X., and Sun, X. (2019). PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation. arXiv.
36. Li, X., Li, F., Pan, L., Chen, Y., Peng, W., Wang, Q., Lyu, Y., and Zhu, Y. (2020). DuEE: A Large-Scale Dataset for Chinese Event Extraction in Real-World Scenarios. Natural Language Processing and Chinese Computing, Springer.10.1007/978-3-030-60457-8_44 ↗
37. Adversarial Image Perturbations with Distortions Weighted by Color on Deep Neural Networks10.1007/s11042-022-12941-w ↗