Lune

ACL Findings2021

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Yubin Wang, Bin Wang

Abstract

Event detection tends to struggle when it needs to recognize novel event types with a few samples. The previous work attempts to solve this problem in the identify-then-classify manner but ignores the trigger discrepancy between event types, thus suffering from the error propagation. In this paper, we present a novel unified model which converts the task to a few-shot tagging problem with a double-part tagging scheme. To this end, we first propose the Prototypical Amortized Conditional Random Field (PA-CRF) to model the label dependency in the few-shot scenario, which approximates the transition scores between labels based on the label prototypes. Then Gaussian distribution is introduced for modeling of the transition scores to alleviate the uncertain estimation resulting from insufficient data. Experimental results show that the unified models work better than existing identifythen-classify models and our PA-CRF further achieves the best results on the benchmark dataset FewEvent. Our code and data are available at http://github.com/congxin95/ PA-CRF.

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.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Few-shot Event Detection: An Empirical Study and a Unified View cites Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
  • Few-shot Event Detection: An Empirical Study and a Unified View cites Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
  • Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning cites Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Exploring Modular Task Decomposition in Cross-domain Named Entity RecognitionXinghua Zhang, Bowen Yu, Yubin Wang, Tingwen Liu et al.SIGIR 2022 · 18 citations
  2. Zero- and Few-Shot Event Detection via Prompt-Based Meta LearningZhenrui Yue, Huimin Zeng, Mengfei Lan, Heng Ji et al.ACL 2023 · 11 citations
  3. Few-shot Event Detection: An Empirical Study and a Unified ViewYubo Ma, Zehao Wang, Yixin Cao, Aixin SunACL 2023 · 7 citations

Builds on3

  1. Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor LearningYi Yang, Arzoo KatiyarEMNLP 2020 · 198 citations
  2. 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
  3. Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic RelationShiyao Cui, Bowen Yu, Tingwen Liu, Zhenyu Zhang et al.EMNLP Findings 2020 · 117 citations

Related papers

  1. HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive ThresholdRuihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang et al.EMNLP Findings 2022 · 16 citations
  2. Taxonomy-aware Learning for Few-Shot Event DetectionJianming Zheng, Fei Cai, Wanyu Chen, Wengqiang Lei et al.WWW 2021 · 22 citations
  3. Knowledge-Enhanced Self-Supervised Prototypical Network for Few-Shot Event DetectionKailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo et al.EMNLP Findings 2022 · 10 citations
  4. 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
  5. Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional NetworksGuangxing Han, Yicheng He, Shiyuan Huang, Jiawei Ma et al.ICCV 2021 · 134 citations
Dusk over the sea between two cliffs drawn in fine vertical lines