Few-shot Incremental Event Detection
Authors: 
Hao Wang, Hanwen Shi, Jianyong DuanAuthors Info & Claims
Article No.: 34, Pages 1 - 20
Abstract
Event detection tasks can enable the quick detection of events from texts and provide powerful support for downstream natural language processing tasks. Most such methods can only detect a fixed set of predefined event classes. To extend them to detect a new class without losing the ability to detect old classes requires costly retraining of the model from scratch. Incremental learning can effectively solve this problem, but it requires abundant data of new classes. In practice, however, the lack of high-quality labeled data of new event classes makes it difficult to obtain enough data for model training. To address the above mentioned issues, we define a new task, few-shot incremental event detection, which focuses on learning to detect a new event class with limited data, while retaining the ability to detect old classes to the extent possible. We created a benchmark dataset IFSED for the few-shot incremental event detection task based on FewEvent and propose two benchmarks, IFSED-K and IFSED-KP. Experimental results show that our approach has a higher F1-score than baseline methods and is more stable.
References
[1]
Debanjan Datta. 2019. A small survey on event detection using twitter. ACM Article, 1 (2019), 11.
[2]
Shirong Shen, Tongtong Wu, Guilin Qi, Yuan Fang Li, Gholamreza Haffari, and Sheng Bi. 2021. Adaptive knowledge-enhanced bayesian meta-learning for few-shot event detection. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2417–2429.
[3]
Lizheng Gao, Gang Zhou, Junyong Luo, and Mingjing Lan. 2019. Survey on meta-event extraction. JCSTe 46, 8 (2019), 9–15.
[4]
Wenpeng Yin. 2020. Meta-learning for few-shot natural language processing: A survey. arXiv preprint arXiv:2007.09604.
[5]
Shumin Deng, Ningyu Zhang, Jiaojian Kang, Yichi Zhang, Wei Zhang, and Huajun Chen. 2020. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. In Proceedings of the 13th International Conference on Web Search and Data Mining, 151–159.
[6]
Pengfei Cao, Yubo Chen, Jun Zhao, and Taifeng Wang. 2020. Incremental event detection via knowledge consolidation networks. In Proceedings of the Empirical Methods in Natural Language Processing. 707–717.
[7]
Meng Qu, Tianyu Gao, Louis-Pascal A. C. Xhonneux, and Jian Tang. 2020. Few-shot relation extraction via bayesian meta-learning on relation graphs. In Proceedings of the 37th International Conference on Machine Learning. JMLR.org, 10 pages.
[8]
Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, and Jun Xie. 2020. Improving event detection via open-domain trigger knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 5887–5897.
[9]
Shulin Liu, Yubo Chen, Shizhu He, Kang Liu, and Jun Zhao. 2016. Leveraging framenet to improve automatic event detection. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2134–2143.
[10]
Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Vol. 1, 86–90.
[11]
Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, and Yihongn Gong. 2020. Few-shot class-incremental learning. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12180–12189.
[12]
Snell Jake, Swersky Kevin, and Zemel Richard. 2017. Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems 30 (2017).
[13]
HongMing Yang, XuYao Zhang, Fei Yin, and ChengLin Liu. 2018. Robust classification with convolutional prototype learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3474–3482.
[14]
Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu. 2019. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 374–382.
[15]
Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin. 2019. Learning a unified classifier incrementally via rebalancing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 831–839.
[16]
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
[17]
Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, and Jun Zhao. 2015. Event extraction via dynamic multi-pooling 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 (Volume 1: Long Papers). 167–176.
[18]
Xiao Liu, Zhunchen Luo, and Heyan Huang. 2018. Jointly multiple events extraction via attention-based graph information aggregation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
[19]
Shiyao Cui, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Xuebin Wang, and Jinqiao Shi. 2020. Edge-enhanced graph convolution networks for event detection with syntactic relation. In Findings of the Association for Computational Linguistics: EMNLP 2020.
[20]
Polikar R, Byorick J, Krause S, Marino A, and Moreton M. 2002. Learn++: A classifier independent incremental learning algorithm for supervised neural networks. In Proceedings of the 2002 International Joint Conference on Neural Networks.1742–1747.
[21]
Kirkpatrick J, Pascanu R, and Rabinowitz N. 2016. Overcoming catastrophic forgetting in neural networks. In Proc Natl Acad Sci USA. 114, 13 (2016), 3521–3526.
[22]
Yuwei Cao, Hao Peng, Jia Wu, Yingtong Dou, Jianxin Li, and Philip S Yu. 2021. Knowledge-preserving incremental social event detection via heterogeneous GNNs. In Proceedings of the Web Conference 2021. 3383–3395.
[23]
Yaqing Wang, Quanming Yao, Kwok James T, and Ni Lionel M. 2020. Generalizing from a few examples: A survey on few-shot learning. ACM Computing Surveys 53, 3 (2020), 1–34.
[24]
Jiang Lu, Pinghua Gong, Jieping Ye, and Changshui Zhang. 2020. Learning from very few samples: A survey. arXiv:2009.02653. Retrieved from https://arxiv.org/abs/2009.02653
[25]
Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Wang Yubin, and Bin Wang. 2021. Few-shot event detection with prototypical amortized conditional random field. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 28–40.
[26]
Jianming Zheng, Fei Cai, Wanyu Chen, Wengqiang Lei, and Honghui Chen. 2021. Taxonomy-aware learning for few-shot event detection. In Proceedings of the Web Conference 2021. 3546–3557.
[27]
Sha Li, Liyuan Liu, Yiqing Xie, Heng Ji, and Jiawei Han. 2022. P4e: Few-shot event detection as prompt-guided identification and localization. arXiv preprint arXiv:2202.07615.
[28]
Mengye Ren, Renjie Liao, Ethan Fetaya, and Richard S. Zemel. 2019. Incremental few-shot learning with attention attractor networks. In Proceedings of the Advances in Neural Information Processing Systems.
[29]
Yoon Sung Whan, Kim Do-Yeon, Seo Jun, and Moon Jaekyun. 2020. XtarNet: Learning to extract task-adaptive representation for incremental few-shot learning. In Proceedings of the 37th International Conference on Machine Learning. 9.
[30]
Songlin Dong, Xiaopeng Hong, Xiaoyu Tao, Xinyuan Chang, Xing Wei, and Yihong Gong. 2021. Few-shot class-incremental learning via relation knowledge distillation. In Proceedings of the AAAI Conference on Artificial Intelligence.
[31]
Congying Xia, Wenpeng Yin, Yihao Feng, and Philip Yu. 2021. Incremental few-shot text classification with multi-round new classes: Formulation, dataset and system. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1351–1360.
Index Terms
- Few-shot Incremental Event Detection
Recommendations
Incremental event detection via an improved knowledge distillation based model
AbstractEvent detection (ED) is of fundamental importance for many information extraction tasks. But conventional ED models require a fixed set of pre-defined event types. When an event trigger that cannot be categorized as any of these types ...
Taxonomy-aware Learning for Few-Shot Event Detection
WWW '21: Proceedings of the Web Conference 2021Event detection classifies unlabeled sentences into event labels, which can benefit numerous applications, including information retrieval, question answering and script learning. One of the major obstacles to event detection in reality is insufficient ...
Multimedia Event Detection Using Event-Driven Multiple Instance Learning
MM '15: Proceedings of the 23rd ACM international conference on MultimediaA complex event can be recognized by observing necessary evidences. In the real world scenarios, this is a difficult task because the evidences can happen anywhere in a video. A straightforward solution is to decompose the video into several segments ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
February 2024
340 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 February 2024
Online AM: 02 December 2023
Accepted: 20 November 2023
Revised: 11 September 2023
Received: 23 August 2022
Published in TALLIP Volume 23, Issue 2
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- R&D Program of Beijing Municipal Education Commission
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 152Total Downloads
- Downloads (Last 12 months)152
- Downloads (Last 6 weeks)12
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in