mlsanityData to 7 Oct 2026

Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention

arXiv 2109.05747 ↗First posted 13 Sep 2021cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Event detection has long been troubled by the trigger curse: overfitting the trigger will harm the generalization ability while underfitting it will hurt the detection performance. This problem is even more severe in few-shot scenario. In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view. By formulating FSED with a structural causal model (SCM), we found that the trigger is a confounder of the context and the result, which makes previous FSED methods much easier to overfit triggers. To resolve this problem, we propose to intervene on the context via backdoor adjustment during training. Experiments show that our method significantly improves the FSED on ACE05, MAVEN and KBP17 datasets.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 22 of its 50 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

22 of 50 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  4. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  5. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  6. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  7. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  8. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  9. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
  10. 2020Interventional Few-Shot Learningcited by 112
  11. 2020Visual Commonsense R-CNNcited by 106
  12. 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 103
10 more
  1. 2019Two Causal Principles for Improving Visual Dialogcited by 75
  2. 2019Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detectioncited by 54
  3. 2019Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networkscited by 33
  4. 2021De-biasing Distantly Supervised Named Entity Recognition via Causal Interventioncited by 24
  5. 2020Few-Shot Event Detection with Prototypical Amortized Conditional Random Fieldcited by 20
  6. 2020Extensively Matching for Few-shot Learning Event Detectioncited by 18
  7. 2018Nugget Proposal Networks for Chinese Event Detectioncited by 11
  8. 2020Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extractioncited by 11
  9. 2021Element Intervention for Open Relation Extractioncited by 11
  10. 2019Cost-sensitive Regularization for Label Confusion-aware Event Detectioncited by 5

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 4; 2024: 1.

9 papers.

  1. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  2. 2023The Devil is in the Details: On the Pitfalls of Event Extraction Evaluationcited by 18
  3. 2022The Art of Prompting: Event Detection based on Type Specific Promptscited by 9
  4. 2023Few-shot Event Detection: An Empirical Study and a Unified Viewcited by 5
  5. 2024Targeted Augmentation for Low-Resource Event Extractioncited by 4
  6. 2022Event Extraction: A Surveycited by 3
  7. 2023Zero- and Few-Shot Event Detection via Prompt-Based Meta Learningcited by 2
  8. 2022P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localizationcited by 1
  9. 2023MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detectioncited by 1