Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 899–914 August 1–6, 2021. ©2021 Association for Computational Linguistics 899 Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech Yi-Ling Chung1,2, Serra Sinem Tekiro˘glu1, and Marco Guerini1 1Fondazione Bruno Kessler, Via Sommarive 18, Povo, Trento, Italy 2University of Trento, Italy ychung@fbk.eu, tekiroglu@fbk.eu, guerini@fbk.eu Abstract Tackling online hatred using informed textual responses – called counter narratives – has been brought under the spotlight recently. Ac- cordingly, a research line has emerged to au- tomatically generate counter narratives in or- der to facilitate the direct intervention in the hate discussion and to prevent hate content from further spreading. Still, current neural approaches tend to produce generic/repetitive responses and lack grounded and up-to-date evidence such as facts, statistics, or examples. Moreover, these models can create plausible but not necessarily true arguments. In this pa- per we present the first complete knowledge- bound counter narrative generation pipeline, grounded in an external knowledge repository that can provide more informative content to fight online hatred. Together with our ap- proach, we present a series of experiments that show its feasibility to produce suitable and in- formative counter narratives in in-domain and cross-domain settings. 1 Introduction Standard approaches for online hate mitigation gen- erally rely on content moderation, ranging from deletion of hate content and suspension of user accounts to shadow banning. However, these ap- proaches may draw limits on free speech and di- verse opinions. An alternative approach is to di- rectly intervene in the conversation with counter narratives. A Counter Narrative (CN) is a non- negative response to a Hate Speech (HS), target- ing and contradicting extreme statements with fact- bound arguments or alternative viewpoints (Be- nesch, 2014; Schieb and Preuss, 2016). Such strat- egy seeks to de-escalate the conversation, disen- gage from hateful sentiment and encourage mu- tual understanding through exchange of opinions. Many Non-Governmental Organizations (NGOs) specialized in hate countering are already adopt- ing this approach by training operators to compose counter narratives. According to NGO guidelines1, proper CNs should also include credible evidence. HS: The world would be a better place without Muslims. They are only killing and raping our children. CN1: Evidence for this? This is not true. How can you say this about an entire faith? CN2: On the contrary, most children abuse is operated by people they know: a relative, family friends, sports coach, someone in a position of trust and authority. Besides, Muslims help people - A Muslim woman rushed to help the victims of a triple stabbing in Manchester on New Year’s Eve. CN3: You are truly one stupid backwards thinking idiot to comment on Muslims like that. Table 1: An example hate speech with appropriate counter narratives (CN1 and CN2) and an inappropriate one (CN3) containing abusive language. In Table 1, we present an HS along with several CNs. Although CN1 and CN2 are both appropriate responses, not all appropriate CNs are equally effec- tive (Silverman et al., 2016; Tuck and Silverman, 2016). CN2 is expected to …

Content truncated to 500 words