A Checkpoint on Multilingual Misogyny Identification

Arianna Muti, Alberto Barrón-Cedeño


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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.acl-srw.37.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2022.acl-srw.37.mp4