A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
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 of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.
Code (1)
Tasks
coreference-resolutionCoreference ResolutioncounterfactualData AugmentationDecision MakingEvent Coreference ResolutionSimilar Papers 제목 키워드 기반
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these meth…
counterfactualData AugmentationText GenerationvalidThought-Path Contrastive Learning via Premise-Oriented Data Augmentation for Logical Reading Comprehension
Logical reading comprehension is a challenging task that entails grasping the underlying semantics of text and applying reasoning to deduce the correct answer. Prior researches have primarily focused on enhancing logical…
Contrastive LearningcounterfactualData AugmentationLogical Reasoning+1EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification
Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augmen…
counterfactualData AugmentationFact VerificationMaking a (Counterfactual) Difference One Rationale at a Time
Rationales, snippets of extracted text that explain an inference, have emerged as a popular framework for interpretable natural language processing (NLP). Rationale models typically consist of two cooperating modules: a …
counterfactualData AugmentationA Rationale-Centric Framework for Human-in-the-loop Machine Learning
We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using stat…
BIG-bench Machine LearningFew-Shot Learning