# Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification

arXiv: https://arxiv.org/abs/2108.12844 · HTML: https://mlsanity.com/paper/2108.12844/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 29 Aug 2021.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [MAVEN: A Massive General Domain Event Detection Dataset](https://mlsanity.com/paper/2004.13590/) (2020)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference](https://mlsanity.com/paper/1907.04380/) (2019)
- [The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task](https://mlsanity.com/paper/1702.01841/) (2017)
- [Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker](https://mlsanity.com/paper/2105.14924/) (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)
- [HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference](https://mlsanity.com/paper/2003.02756/) (2020)
- [An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference](https://mlsanity.com/paper/2010.03777/) (2020)
- [Nugget Proposal Networks for Chinese Event Detection](https://mlsanity.com/paper/1805.00249/) (2018)
- [Event Nugget Detection with Forward-Backward Recurrent Neural Networks](https://mlsanity.com/paper/1802.05672/) (2018)
- [Exploiting the Matching Information in the Support Set for Few Shot Event Classification](https://mlsanity.com/paper/2002.05295/) (2020)
- [Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference](https://mlsanity.com/paper/2010.03760/) (2020)

## Built on by (most cited first, 8 of 8)

- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling](https://mlsanity.com/paper/2109.13023/) (2021)
- [Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation](https://mlsanity.com/paper/2210.04497/) (2022)
- [Enhancing Continual Relation Extraction via Classifier Decomposition](https://mlsanity.com/paper/2305.04636/) (2023)
- [DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade](https://mlsanity.com/paper/2305.14751/) (2023)
- [Event Detection Explorer: An Interactive Tool for Event Detection Exploration](https://mlsanity.com/paper/2204.12456/) (2022)
- [MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection](https://mlsanity.com/paper/2305.09335/) (2023)
- [Causal Interventions-based Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2305.01914/) (2023)

## Abstract (arXiv)

Few-Shot Event Classification (FSEC) aims at developing a model for event prediction, which can generalize to new event types with a limited number of annotated data. Existing FSEC studies have achieved high accuracy on different benchmarks. However, we find they suffer from trigger biases that signify the statistical homogeneity between some trigger words and target event types, which we summarize as trigger overlapping and trigger separability. The biases can result in context-bypassing problem, i.e., correct classifications can be gained by looking at only the trigger words while ignoring the entire context. Therefore, existing models can be weak in generalizing to unseen data in real scenarios. To further uncover the trigger biases and assess the generalization ability of the models, we propose two new sampling methods, Trigger-Uniform Sampling (TUS) and COnfusion Sampling (COS), for the meta tasks construction during evaluation. Besides, to cope with the context-bypassing problem in FSEC models, we introduce adversarial training and trigger reconstruction techniques. Experiments show these techniques help not only improve the performance, but also enhance the generalization ability of models.