Abstract
This paper describes our system used in the SemEval-2023 \textit{Task 10 Explainable Detection of Online Sexism (EDOS)}. Specifically, we participated in subtask B: a 4-class sexism classification task, and subtask C: a more fine-grained (11-class) sexism classification task, where it is necessary to predict the category of sexism. We treat these two subtasks as one multi-label hierarchical text classification problem, and propose an integrated sexism detection model for improving the performance of the sexism detection task. More concretely, we use the pre-trained BERT model to encode the text and class label and a hierarchy-relevant structure encoder is employed to model the relationship between classes of subtasks B and C. Additionally, a self-training strategy is designed to alleviate the imbalanced problem of distribution classes. Extensive experiments on subtasks B and C demonstrate the effectiveness of our proposed approach.- Anthology ID:
- 2023.semeval-1.129
- Volume:
- Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 934–940
- Language:
- URL:
- https://aclanthology.org/2023.semeval-1.129
- DOI:
- 10.18653/v1/2023.semeval-1.129
- Cite (ACL):
- Ziyi Yao, Heyan Chai, Jinhao Cui, Siyu Tang, and Qing Liao. 2023. HITSZQ at SemEval-2023 Task 10: Category-aware Sexism Detection Model with Self-training Strategy. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 934–940, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- HITSZQ at SemEval-2023 Task 10: Category-aware Sexism Detection Model with Self-training Strategy (Yao et al., SemEval 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.semeval-1.129.pdf