English

ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection

Computation and Language 2020-08-17 v1

Abstract

This paper describes our participation in SemEval-2020 Task 12: Multilingual Offensive Language Detection. We jointly-trained a single model by fine-tuning Multilingual BERT to tackle the task across all the proposed languages: English, Danish, Turkish, Greek and Arabic. Our single model had competitive results, with a performance close to top-performing systems in spite of sharing the same parameters across all languages. Zero-shot and few-shot experiments were also conducted to analyze the transference performance among these languages. We make our code public for further research

Keywords

Cite

@article{arxiv.2008.06408,
  title  = {ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection},
  author = {Juan Manuel Pérez and Aymé Arango and Franco Luque},
  journal= {arXiv preprint arXiv:2008.06408},
  year   = {2020}
}

Comments

Github repo: https://github.com/finiteautomata/offenseval2020

R2 v1 2026-06-23T17:51:48.110Z