Generating Commonsense Counterfactuals for Stable Relation Extraction
Submission Type: Regular Long Paper
Submission Track: Information Extraction
Submission Track 2: Natural Language Generation
Keywords: Counterfactual Data Augmentation, Commonsense-constrained Generation, Relation Extraction
TL;DR: We propose a commonsense-constrained counterfactual data augmentation method for relation extraction tasks.
Abstract: Recent studies on counterfactual augmented data have achieved great success in the coarse-grained natural language processing tasks. However, existing methods encounter two major problems when dealing with the fine-grained relation extraction tasks. One is that they struggle to accurately identify causal terms under the invariant entity constraint. The other is that they ignore the commonsense constraint. To solve these problems, we propose a novel framework to generate commonsense counterfactuals for stable relation extraction. Specifically, to identify causal terms accurately, we introduce an intervention-based strategy and leverage a constituency parser for correction. To satisfy the commonsense constraint, we introduce the concept knowledge base WordNet and design a bottom-up relation expansion algorithm on it to uncover commonsense relations between entities. We conduct a series of comprehensive evaluations, including the low-resource, out-of-domain, and adversarial-attack settings. The results demonstrate that our framework significantly enhances the stability of base relation extraction models.
Submission Number: 1075
Loading