HULAT at SemEval-2023 Task 10: Data augmentation for pre-trained transformers applied to the detection of sexism in social media
This work addresses the problem of automated sexism detection for social media analysis, but it is incremental as it applies existing methods to a specific competition task.
The paper tackled the detection of sexism in social media by exploring transformer models and data augmentation techniques, achieving best results with RoBERTa and augmentation for some tasks but not improving in others, with all code made available.
This paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as BERT, DistilBERT, RoBERTa, and XLNet. We also study different data augmentation techniques to increase the training dataset. During the development phase, our best results were obtained by using RoBERTa and data augmentation for tasks B and C. However, the use of synthetic data does not improve the results for task C. We participated in the three subtasks. Our approach still has much room for improvement, especially in the two fine-grained classifications. All our code is available in the repository https://github.com/isegura/hulat_edos.