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

arXiv: https://arxiv.org/abs/2109.05747 · HTML: https://mlsanity.com/paper/2109.05747/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [MAVEN: A Massive General Domain Event Detection Dataset](https://mlsanity.com/paper/2004.13590/) (2020)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks](https://mlsanity.com/paper/1906.03783/) (2019)
- [De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention](https://mlsanity.com/paper/2106.09233/) (2021)
- [Few-Shot Event Detection with Prototypical Amortized Conditional Random Field](https://mlsanity.com/paper/2012.02353/) (2020)
- [Extensively Matching for Few-shot Learning Event Detection](https://mlsanity.com/paper/2006.10093/) (2020)
- [Nugget Proposal Networks for Chinese Event Detection](https://mlsanity.com/paper/1805.00249/) (2018)
- [Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction](https://mlsanity.com/paper/2010.11325/) (2020)
- [Element Intervention for Open Relation Extraction](https://mlsanity.com/paper/2106.09558/) (2021)
- [Cost-sensitive Regularization for Label Confusion-aware Event Detection](https://mlsanity.com/paper/1906.06003/) (2019)

## Built on by (most cited first, 9 of 9)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation](https://mlsanity.com/paper/2306.06918/) (2023)
- [The Art of Prompting: Event Detection based on Type Specific Prompts](https://mlsanity.com/paper/2204.07241/) (2022)
- [Few-shot Event Detection: An Empirical Study and a Unified View](https://mlsanity.com/paper/2305.01901/) (2023)
- [Targeted Augmentation for Low-Resource Event Extraction](https://mlsanity.com/paper/2405.08729/) (2024)
- [Event Extraction: A Survey](https://mlsanity.com/paper/2210.03419/) (2022)
- [Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning](https://mlsanity.com/paper/2305.17373/) (2023)
- [P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization](https://mlsanity.com/paper/2202.07615/) (2022)
- [MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection](https://mlsanity.com/paper/2305.09335/) (2023)

## 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.