Graph Enhanced Representation and Reasoning Model for Tabular Fact Verification

Abstract

Tabular fact verification is a challenging task that requires obtaining relevant evidence from the table and utilizing them to verify a given claim. The main difficulty in tabular fact verification is that traditional language models cannot capture the underlying information carried in tabular data. To solve this problem, we propose GraERR, a Graph Enhanced Representation and Reasoning Model for Tabular Fact Verification. It consists of two modules: a data initial representation module based on the DeBERTa model and a graph-augmented representation and inference module. The former improves the inference ability of the model with a DeBERTa model pre-trained on the natural language inference dataset. The graph enhancement module enhances the model’s ability to learn table representations by effectively integrating textual and structural information in tables. The best results obtained experimentally on the InfoTabs dataset demonstrate the effectiveness of the GECMT model on the tabular fact verification task.