EMNLP Findings2022
HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold
Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, Dangyang Chen
Abstract
Conventional event detection models under supervised learning settings suffer from the inability of transfer to newly-emerged event types owing to lack of sufficient annotations. A commonly-adapted solution is to follow a identify-then-classify manner, which first identifies the triggers and then converts the classification task via a few-shot learning paradigm. However, these methods still fall far short of expectations due to: (i) insufficient learning of discriminative representations in low-resource scenarios, and (ii) trigger misidentification caused by the overlap of the learned representations of triggers and non-triggers. To address the problems, in this paper, we propose a novel Hybrid Contrastive Learning method with a Task-Adaptive Threshold (abbreviated as HCL-TAT), which enables discriminative representation learning with a two-view contrastive loss (support-support and prototype-query), and devises an easily-adapted threshold to alleviate misidentification of triggers. Extensive experiments on the benchmark dataset FewEvent demonstrate the superiority of our method to achieve better results compared to the state-ofthe-arts. All the code and data of this paper are available at https://github.com/CCIIPLab/ HCL-TAT.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning cites A Simple Framework for Contrastive Learning of Visual Representations
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning cites Supervised Contrastive Learning
- Supervised Contrastive Learning cites A Simple Framework for Contrastive Learning of Visual Representations
Builds on9
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
- Supervised Contrastive LearningPrannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna et al.NeurIPS 2020 · 7,049 citations
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningBeliz Gunel, Jingfei Du, Alexis Conneau, Veselin StoyanovICLR 2021 · 595 citations
- Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection NetworkYutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou et al.ACL 2020 · 186 citations
- Improving Event Detection via Open-domain Trigger KnowledgeMeihan Tong, Bin Xu, Shuai Wang, Yixin Cao et al.ACL 2020 · 107 citations
Related papers
- Zero- and Few-Shot Event Detection via Prompt-Based Meta LearningZhenrui Yue, Huimin Zeng, Mengfei Lan, Heng Ji et al.ACL 2023 · 11 citations
- Few-Shot Event Detection with Prototypical Amortized Conditional Random FieldXin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu et al.ACL Findings 2021 · 51 citations
- Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event DetectionShirong Shen, Tongtong Wu, Guilin Qi, Yuan-Fang Li et al.ACL Findings 2021 · 39 citations
- Exploring Task Difficulty for Few-Shot Relation ExtractionJiale Han, Bo Cheng, Wei LuEMNLP 2021 · 74 citations
- FSCE: Few-Shot Object Detection via Contrastive Proposal EncodingBo Sun, Banghuai Li, Shengcai Cai, Ye Yuan et al.CVPR 2021
