Cross-lingual Capsule Network for Hate Speech Detection in Social Media

TL;DR

This paper introduces a cross-lingual capsule network model with lexical semantics for hate speech detection, achieving state-of-the-art results across English, Spanish, and Italian datasets, enhancing multilingual hate speech analysis.

Contribution

The paper presents a novel cross-lingual capsule network model with domain-specific lexical semantics for improved hate speech detection across multiple languages.

Findings

Achieved state-of-the-art performance on benchmark datasets.

Outperformed existing baselines on all six language pairs.

Effective cross-lingual transfer of hate speech detection resources.

Abstract

Most hate speech detection research focuses on a single language, generally English, which limits their generalisability to other languages. In this paper we investigate the cross-lingual hate speech detection task, tackling the problem by adapting the hate speech resources from one language to another. We propose a cross-lingual capsule network learning model coupled with extra domain-specific lexical semantics for hate speech (CCNL-Ex). Our model achieves state-of-the-art performance on benchmark datasets from AMI@Evalita2018 and AMI@Ibereval2018 involving three languages: English, Spanish and Italian, outperforming state-of-the-art baselines on all six language pairs.