Table-based Fact Verification with Salience-aware Learning

Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely available. Moreover, training a generalized fact verification model requires abundant labeled training data. In this paper, we propose a novel system to address these problems. Inspired by counterfactual causality, our system identifies token-level salience in the statement with probing-based salience estimation. Salience estimation allows enhanced learning of fact verification from two perspectives. From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement. From the other perspective, our system applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms. Experimental results on TabFact show the effective improvement by the proposed salience-aware learning techniques, leading to the new SOTA performance on the benchmark. Our code is publicly available at .

PDF Abstract Findings (EMNLP) 2021 PDF Findings (EMNLP) 2021 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Table-based Fact Verification TabFact Salience-aware TAPAS Test 82.1 # 3
Val 82.7 # 3


No methods listed for this paper. Add relevant methods here