Abstract
We address the problem of identifying misogyny in tweets in mono and multilingual settings in three languages: English, Italian, and Spanish. We explore model variations considering single and multiple languages both in the pre-training of the transformer and in the training of the downstream taskto explore the feasibility of detecting misogyny through a transfer learning approach across multiple languages. That is, we train monolingual transformers with monolingual data, and multilingual transformers with both monolingual and multilingual data. Our models reach state-of-the-art performance on all three languages. The single-language BERT models perform the best, closely followed by different configurations of multilingual BERT models. The performance drops in zero-shot classification across languages. Our error analysis shows that multilingual and monolingual models tend to make the same mistakes.- Anthology ID:
- 2022.acl-srw.37
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Samuel Louvan, Andrea Madotto, Brielen Madureira
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 454–460
- Language:
- URL:
- https://aclanthology.org/2022.acl-srw.37
- DOI:
- 10.18653/v1/2022.acl-srw.37
- Cite (ACL):
- Arianna Muti and Alberto Barrón-Cedeño. 2022. A Checkpoint on Multilingual Misogyny Identification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 454–460, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- A Checkpoint on Multilingual Misogyny Identification (Muti & Barrón-Cedeño, ACL 2022)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2022.acl-srw.37.pdf