Reasoning Over Semantic-Level Graph for Fact Checking

Abstract

Fact checking is a challenging task because verifying the truthfulness of a claim requires reasoning about multiple retrievable evidence. In this work, we present a method suitable for reasoning about the semantic-level structure of evidence. Unlike most previous works, which typically represent evidence sentences with either string concatenation or fusing the features of isolated evidence sentences, our approach operates on rich semantic structures of evidence obtained by semantic role labeling. We propose two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet. Specifically, using XLNet as the backbone, we first utilize the graph structure to re-define the relative distances of words, with the intuition that semantically related words should have short distances. Then, we adopt graph convolutional network and graph attention network to propagate and aggregate information from neighboring nodes on the graph. We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy. Our model is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.

Fine-grained Fact Verification with Kernel Graph Attention Network

“…It conducts reasoning and aggregation over claim evidence pairs with a graph model (Veličković et al, 2017;Scarselli et al, 2008;Kipf and Welling, 2017). Zhong et al (2019) further employs XLNet and establishes a semantic-level graph for reasoning for a better performance. These graph based models establish node interactions for joint reasoning over several evidence pieces.…”

Explainable Automated Fact-Checking for Public Health Claims

“…We then select the top k sentences for veracity prediction. As with sentence selection approaches from the fact-checking literature (Nie et al, 2019;Zhong et al, 2019), we choose k = 5.…”

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification

“…propose a kernel graph attention network that conducts more fine-grained evidence selection and reasoning. Zhong et al (2020b) construct a semanticlevel graph and present two graph-driven representation learning mechanisms to perform reasoning over the claim-evidence graph.…”

“…It is well accepted that symbolic information (such as count and only) plays a great role in understanding semi-structured evidence based statements (Wenhu Chen and Wang, 2020). However, most existing approaches for fact verification (Thorne et al, 2018;Nie et al, 2019;Zhong et al, 2020b;Soleimani et al, 2020) focus on the understanding of natural language, namely, linguistic reasoning, but fail to consider symbolic information, which plays an important role in complex reasoning (Liang et al, 2017;Dua et al, 2019;. Due to the diversity of natural language expressions, it is difficult to capture symbolic information effectively from natural language directly.…”