A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution

arXiv:2404.01921v1 Announce Type: new
Abstract: Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability …

abstract arxiv augmentation clustering counterfactual cs.cl data document documents event events however language language models performance reliance resolution systems text type