Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
This work addresses the data scarcity issue in event causality identification for NLP applications, offering a novel method that enhances performance on specific benchmarks.
The paper tackles the limited labeled data problem in event causality identification by proposing CauSeRL, a self-supervised approach that learns causal patterns from external statements and transfers them to the target model, achieving F1 improvements of +2.0 and +3.4 points on EventStoryLine and Causal-TimeBank datasets.
Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficient support for models to capture useful indicators from causal statements, especially for handing those new, unseen cases. To alleviate this problem, we propose a novel approach, shortly named CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. Then, we adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model. Experimental results show that our method significantly outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively).