Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech
This addresses the need for more effective automated interventions against online hate speech by providing evidence-based responses, though it appears incremental as an enhancement to existing neural approaches.
The paper tackles the problem of generating generic and ungrounded counter narratives for hate speech by introducing the first complete knowledge-grounded pipeline that uses an external knowledge repository. Experiments demonstrate its feasibility in producing suitable and informative counter narratives in both in-domain and cross-domain settings.
Tackling online hatred using informed textual responses - called counter narratives - has been brought under the spotlight recently. Accordingly, a research line has emerged to automatically generate counter narratives in order 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 paper 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 approach, we present a series of experiments that show its feasibility to produce suitable and informative counter narratives in in-domain and cross-domain settings.