Generating Fact Checking Explanations

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7352–7364 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 7352 Generating Fact Checking Explanations Pepa Atanasova Jakob Grue Simonsen Christina Lioma Isabelle Augenstein Department of Computer Science University of Copenhagen Denmark {pepa, simonsen, c.lioma, augenstein}@di.ku.dk Abstract Most existing work on automated fact check- ing is concerned with predicting the veracity of claims based on metadata, social network spread, language used in claims, and, more re- cently, evidence supporting or denying claims. A crucial piece of the puzzle that is still miss- ing is to understand how to automate the most elaborate part of the process – generating jus- tifications for verdicts on claims. This paper provides the first study of how these expla- nations can be generated automatically based on available claim context, and how this task can be modelled jointly with veracity predic- tion. Our results indicate that optimising both objectives at the same time, rather than train- ing them separately, improves the performance of a fact checking system. The results of a manual evaluation further suggest that the in- formativeness, coverage and overall quality of the generated explanations are also improved in the multi-task model. 1 Introduction When a potentially viral news item is rapidly or indiscriminately published by a news outlet, the responsibility of verifying the truthfulness of the item is often passed on to the audience. To alle- viate this problem, independent teams of profes- sional fact checkers manually verify the veracity and credibility of common or particularly check- worthy statements circulating the web. However, these teams have limited resources to perform man- ual fact checks, thus creating a need for automating the fact checking process. The current research landscape in automated fact checking is comprised of systems that esti- mate the veracity of claims based on available metadata and evidence pages. Datasets like LIAR (Wang, 2017) and the multi-domain dataset Mul- tiFC (Augenstein et al., 2019) provide real-world Claim: The last major oil spill from a drilling accident in America happened over 40 years ago in 1969. Ruling Comments: (...) The last major oil spill from a drilling accident in America happened over 40 years ago in 1969. (...) The largest in volume was the Santa Barbara spill of 1969 referenced by Murdock and Johnson, in which an estimated 100,000 barrels of oil spilled into the Pacific Ocean, according to the API. The Santa Barbara spill was so big it ranked seventh among the 10 largest oil spills caused by marine well blowouts in the world, the report states. Two other U.S. spills, both in 1970, rank eighth and 10th. Fourteen marine blowouts have taken place in the U.S. between 1969 and 2007. Six of them took place after 1990 and spilled a total of nearly 13,700 barrels. (...) We interviewed three scientists who said that the impact of a spill has little to do with its volume. Scientists have proven that spills far smaller than Santa Barbara’s have been …

Content truncated to 500 words