English

Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification

Computation and Language 2022-05-18 v1

Abstract

In this paper, we tackle the Arabic Fine-Grained Hate Speech Detection shared task and demonstrate significant improvements over reported baselines for its three subtasks. The tasks are to predict if a tweet contains (1) Offensive language; and whether it is considered (2) Hate Speech or not and if so, then predict the (3) Fine-Grained Hate Speech label from one of six categories. Our final solution is an ensemble of models that employs multitask learning and a self-consistency correction method yielding 82.7% on the hate speech subtask -- reflecting a 3.4% relative improvement compared to previous work.

Keywords

Cite

@article{arxiv.2205.07960,
  title  = {Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification},
  author = {Badr AlKhamissi and Mona Diab},
  journal= {arXiv preprint arXiv:2205.07960},
  year   = {2022}
}

Comments

Accepted at the 5th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT5/LREC 2022)

R2 v1 2026-06-24T11:19:09.407Z