Combining Fact Extraction and Verification with Neural Semantic Matching Networks

TL;DR

This paper introduces a neural semantic matching approach for fact verification that jointly handles document retrieval, sentence selection, and claim verification, achieving state-of-the-art results on the FEVER dataset.

Contribution

It presents a unified neural semantic matching framework for all three fact verification subtasks, integrating evidence retrieval and claim verification with enhanced semantic features.

Findings

Neural semantic matching outperforms TF-IDF and encoder models in evidence retrieval.

Adding relatedness scores and WordNet features improves NLI claim verification.

The integrated model achieves state-of-the-art results on FEVER dataset.

Abstract

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recently-released FEVER dataset introduced a benchmark fact-verification task in which a system is asked to verify a claim using evidential sentences from Wikipedia documents. In this paper, we present a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification. For evidence retrieval (document retrieval and sentence selection), unlike traditional vector space IR models in which queries and sources are matched in some pre-designed term vector space, we develop neural models to perform deep semantic matching from raw textual input, assuming no intermediate term representation and no access to structured external knowledge bases. We also show that Pageview frequency can also help improve the performance of evidence retrieval results, that later can be matched by using our neural semantic matching network. For claim verification, unlike previous approaches that simply feed upstream retrieved evidence and the claim to a natural language inference (NLI) model, we further enhance the NLI model by providing it with internal semantic relatedness scores (hence integrating it with the evidence retrieval modules) and ontological WordNet features. Experiments on the FEVER dataset indicate that (1) our neural semantic matching method outperforms popular TF-IDF and encoder models, by significant margins on all evidence retrieval metrics, (2) the additional relatedness score and WordNet features improve the NLI model via better semantic awareness, and (3) by formalizing all three subtasks as a similar semantic matching problem and improving on all three stages, the complete model is able to achieve the state-of-the-art results on the FEVER test set.