# IUST_NLP at SemEval-2023 Task 10: Explainable Detecting Sexism with Transformers and Task-adaptive Pretraining

arXiv: https://arxiv.org/abs/2305.06892 · HTML: https://mlsanity.com/paper/2305.06892/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 11 May 2023.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://mlsanity.com/paper/2303.04222/) (2023)
- [Automatic Sexism Detection with Multilingual Transformer Models](https://mlsanity.com/paper/2106.04908/) (2021)

## Abstract (arXiv)

This paper describes our system on SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). This work aims to design an automatic system for detecting and classifying sexist content in online spaces. We propose a set of transformer-based pre-trained models with task-adaptive pretraining and ensemble learning. The main contributions of our system include analyzing the performance of different transformer-based pre-trained models and combining these models, as well as providing an efficient method using large amounts of unlabeled data for model adaptive pretraining. We have also explored several other strategies. On the test dataset, our system achieves F1-scores of 83%, 64%, and 47% on subtasks A, B, and C, respectively.