The Explainable Detection of Online Sexism task presents the problem of explainable sexism detection through fine-grained categorisation of sexist cases with three subtasks. Our team experimented with different ways to combat class imbalance throughout the tasks using data augmentation and loss alteration techniques. We tackled the challenge by utilising ensembles of Transformer models trained on different datasets, which are tested to find the balance between performance and interpretability. This solution ranked us in the top 40\% of teams for each of the tracks.
@article{arxiv.2305.08636,
title = {AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning},
author = {Adam Rydelek and Daryna Dementieva and Georg Groh},
journal= {arXiv preprint arXiv:2305.08636},
year = {2023}
}
Comments
One of the top solutions at the SemEval-2023 task "The Explainable Detection of Online Sexism"