Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation

TL;DR

This paper introduces a new dataset and a novel two-stage framework for generating counterspeech conditioned on specific intents, improving the diversity and appropriateness of responses to hate speech.

Contribution

It presents IntentCONAN, a diversified intent-specific counterspeech dataset, and QUARC, a two-stage intent-conditioned generation framework with a novel fusion module.

Findings

QUARC outperforms baselines by 10% on evaluation metrics.

Human evaluation confirms more appropriate responses.

Intent-conditioned generation enhances counterspeech diversity.

Abstract

Counterspeech has been demonstrated to be an efficacious approach for combating hate speech. While various conventional and controlled approaches have been studied in recent years to generate counterspeech, a counterspeech with a certain intent may not be sufficient in every scenario. Due to the complex and multifaceted nature of hate speech, utilizing multiple forms of counter-narratives with varying intents may be advantageous in different circumstances. In this paper, we explore intent-conditioned counterspeech generation. At first, we develop IntentCONAN, a diversified intent-specific counterspeech dataset with 6831 counterspeeches conditioned on five intents, i.e., informative, denouncing, question, positive, and humour. Subsequently, we propose QUARC, a two-stage framework for intent-conditioned counterspeech generation. QUARC leverages vector-quantized representations learned for each intent category along with PerFuMe, a novel fusion module to incorporate intent-specific information into the model. Our evaluation demonstrates that QUARC outperforms several baselines by an average of 10% across evaluation metrics. An extensive human evaluation supplements our hypothesis of better and more appropriate responses than comparative systems.