How Robust are Fact Checking Systems on Colloquial Claims?

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1535–1548 June 6–11, 2021. ©2021 Association for Computational Linguistics 1535 How Robust are Fact Checking Systems on Colloquial Claims? Byeongchang Kim∗ Hyunwoo Kim∗ Seokhee Hong Gunhee Kim Seoul National University, Seoul, Korea {byeongchang.kim,hyunw.kim,seokhee.hong}@vl.snu.ac.kr, gunhee@snu.ac.kr https://vl.snu.ac.kr/projects/colloquial-claims Abstract Knowledge is now starting to power neural di- alogue agents. At the same time, the risk of misinformation and disinformation from dia- logue agents also rises. Verifying the veracity of information from formal sources are widely studied in computational fact checking. In this work, we ask: How robust are fact checking systems on claims in colloquial style? We aim to open up new discussions in the intersection of fact verification and dialogue safety. In or- der to investigate how fact checking systems behave on colloquial claims, we transfer the styles of claims from FEVER (Thorne et al., 2018) into colloquialism. We find that exist- ing fact checking systems that perform well on claims in formal style significantly degen- erate on colloquial claims with the same se- mantics. Especially, we show that document retrieval is the weakest spot in the system even vulnerable to filler words, such as “yeah” and “you know”. The document recall of WikiAPI retriever (Hanselowski et al., 2018) which is 90.0% on FEVER, drops to 72.2% on the col- loquial claims. We compare the characteristics of colloquial claims to those of claims in for- mal style, and demonstrate the challenging is- sues in them. 1 Introduction Recently, knowledge has been starting to power neural dialogue agents (Moghe et al., 2018; Zhou et al., 2018b; Ghazvininejad et al., 2018; Qin et al., 2019; Gopalakrishnan et al., 2019), being equipped with Wikipedia (Dinan et al., 2019b), news (Gopalakrishnan et al., 2019), domain spe- cific knowledge-base (Eric and Manning, 2017), and commonsense (Zhou et al., 2018a; Young et al., 2018; Wu et al., 2020). However, the use of knowl- edge inevitably put dialogue agents in new jeop- ardy. For example, recent workshop on safety for conversational AI (Dinan et al., 2020b) introduced ∗Equal contribution an example of such risk: Bickmore et al. (2018) asked participants to query conversational agents for advice in situations where medical information is needed. Then, internist and pharmacist judged the actions that the participants would take based on the advice. Assessments revealed that agents of- ten deliver incorrect medical information that may cause lethal consequences. A bigger threat may be the abuse of dialogue agents to deliberately distribute disinformation. What would happen if knowledge-powered agents are tweaked to massively generate false claims on online communities? The impact of such fake news can be critical as they quickly spread through social media (Shu et al., 2017). The chatbot Tay’s shut down due to malicious attempts show the imminent danger of abuse (Wolf et al., 2017). Verifying the integrity of a given piece of in- formation has been studied in the field of compu- tational fact checking. Thorne et al. (2018) intro- …

Content truncated to 500 words