# Deep Multi-Task Models for Misogyny Identification and Categorization on Arabic Social Media

arXiv: https://arxiv.org/abs/2206.08407 · HTML: https://mlsanity.com/paper/2206.08407/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [ERNIE 2.0: A Continual Pre-training Framework for Language Understanding](https://mlsanity.com/paper/1907.12412/) (2019)
- [ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic](https://mlsanity.com/paper/2101.01785/) (2020)
- [Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language](https://mlsanity.com/paper/2103.10195/) (2021)
- [Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language](https://mlsanity.com/paper/2106.12488/) (2021)
- [BERT-based Multi-Task Model for Country and Province Level Modern Standard Arabic and Dialectal Arabic Identification](https://mlsanity.com/paper/2106.12495/) (2021)

## Built on by (most cited first, 1 of 1)

- [Transformers and Ensemble methods: A solution for Hate Speech Detection in Arabic languages](https://mlsanity.com/paper/2303.09823/) (2023)

## Abstract (arXiv)

The prevalence of toxic content on social media platforms, such as hate speech, offensive language, and misogyny, presents serious challenges to our interconnected society. These challenging issues have attracted widespread attention in Natural Language Processing (NLP) community. In this paper, we present the submitted systems to the first Arabic Misogyny Identification shared task. We investigate three multi-task learning models as well as their single-task counterparts. In order to encode the input text, our models rely on the pre-trained MARBERT language model. The overall obtained results show that all our submitted models have achieved the best performances (top three ranked submissions) in both misogyny identification and categorization tasks.