Cross-lingual Hate Speech Detection using Transformer Models

2021/11/01 by Teodor Tiţa, Tiţa, Teodor, Arkaitz Zubiaga +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.2111.00981

7 pages

arxiv created 2021/11/01 · arxiv updated 2021/11/02

Abstract

Hate speech detection within a cross-lingual setting represents a paramount area of interest for all medium and large-scale online platforms. Failing to properly address this issue on a global scale has already led over time to morally questionable real-life events, human deaths, and the perpetuation of hate itself. This paper illustrates the capabilities of fine-tuned altered multi-lingual Transformer models (mBERT, XLM-RoBERTa) regarding this crucial social data science task with cross-lingual training from English to French, vice-versa and each language on its own, including sections about iterative improvement and comparative error analysis.

Related

• Analysis and Detection of Multilingual Hate Speech Using Transformer Based Deep Learning
• Cross-lingual hate speech detection based on multilingual domain-specific word embeddings
• Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
• Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXEL
• Highly Generalizable Models for Multilingual Hate Speech Detection