Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer

Huiyuan Lai, Antonio Toral, Malvina Nissim


Abstract
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides, in view of the general scarcity of parallel data, we propose a modular approach for multilingual formality transfer, which consists of two training strategies that target adaptation to both language and task. Our approach achieves competitive performance without monolingual task-specific parallel data and can be applied to other style transfer tasks as well as to other languages.
Anthology ID:
2022.acl-short.29
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
262–271
Language:
URL:
https://aclanthology.org/2022.acl-short.29
DOI:
10.18653/v1/2022.acl-short.29
Bibkey:
Cite (ACL):
Huiyuan Lai, Antonio Toral, and Malvina Nissim. 2022. Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 262–271, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer (Lai et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.29.pdf
Video:
 https://aclanthology.org/2022.acl-short.29.mp4
Code
 laihuiyuan/multilingual-tst
Data
GYAFCXFORMAL