English

Cross-lingual Hate Speech Detection using Transformer Models

Computation and Language 2021-11-02 v1

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.

Keywords

Cite

@article{arxiv.2111.00981,
  title  = {Cross-lingual Hate Speech Detection using Transformer Models},
  author = {Teodor Tiţa and Arkaitz Zubiaga},
  journal= {arXiv preprint arXiv:2111.00981},
  year   = {2021}
}

Comments

7 pages

R2 v1 2026-06-24T07:21:03.523Z