GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 892–901 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 892 GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification Jie Zhou1,2,3, Xu Han1,2,3, Cheng Yang1,2,3, Zhiyuan Liu1,2,3† Lifeng Wang4, Changcheng Li4, Maosong Sun1,2,3 1Department of Computer Science and Technology, Tsinghua University, Beijing, China 2Institute for Artificial Intelligence, Tsinghua University, Beijing, China 3State Key Lab on Intelligent Technology and Systems, Tsinghua University, Beijing, China 4Tencent Marketing Solution, Tencent, Shenzhen, China {zhoujie18, hanxu17, cheng-ya14}@mails.tsinghua.edu.cn {fandywang, harrychli}@tencent.com, {liuzy, sms}@tsinghua.edu.cn Abstract Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to ver- ify given claims. Many claims require to si- multaneously integrate and reason over several pieces of evidence for verification. However, previous work employs simple models to ex- tract information from evidence without let- ting evidence communicate with each other, e.g., merely concatenate the evidence for pro- cessing. Therefore, these methods are unable to grasp sufficient relational and logical infor- mation among the evidence. To alleviate this issue, we propose a graph-based evidence ag- gregating and reasoning (GEAR) framework which enables information to transfer on a fully-connected evidence graph and then uti- lizes different aggregators to collect multi- evidence information. We further employ BERT, an effective pre-trained language repre- sentation model, to improve the performance. Experimental results on a large-scale bench- mark dataset FEVER have demonstrated that GEAR could leverage multi-evidence infor- mation for FV and thus achieves the promis- ing result with a test FEVER score of 67.10%. Our code is available at https://github. com/thunlp/GEAR. 1 Introduction Due to the rapid development of information ex- traction (IE), huge volumes of data have been extracted. How to automatically verify the data becomes a vital problem for various data- driven applications, e.g., knowledge graph com- pletion (Wang et al., 2017) and open domain question answering (Chen et al., 2017a). Hence, many recent research efforts have been devoted to fact verification (FV), which aims to verify given claims with the evidence retrieved from plain text. † Corresponding author: Z.Liu(liuzy@tsinghua.edu.cn) “SUPPORTED” Example Claim The Rodney King riots took place in the most populous county in the USA. Evidence (1) The 1992 Los Angeles riots, also known as the Rodney King riots were a series of riots, lootings, ar- sons, and civil disturbances that occurred in Los An- geles County, California in April and May 1992. (2) Los Angeles County, officially the County of Los Angeles, is the most populous county in the USA. “REFUTED” Example Claim Giada at Home was only available on DVD. Evidence (1) Giada at Home is a television show and first aired on October 18, 2008, on the Food Network. (2) Food Network is an American basic cable and satellite television channel. Table 1: Some examples of reasoning over several pieces of evidence together for verification. The italic words are the key information to verify the claim. Both of the claims require to …

Content truncated to 500 words