Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

TL;DR

This paper introduces a novel pipeline for generating knowledge-grounded counter narratives to combat online hate speech, leveraging external knowledge bases to produce more informative and contextually relevant responses.

Contribution

It presents the first complete system for knowledge-bound counter narrative generation, addressing limitations of previous neural models by grounding responses in factual information.

Findings

The approach produces more informative counter narratives.

The system is effective in both in-domain and cross-domain settings.

Experiments demonstrate the feasibility of the method.

Abstract

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.