Abstract
Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant parallel data with a pivot language. Naturally, the key to triangular machine translation is the successful exploitation of such auxiliary data. In this work, we propose a transfer-learning-based approach that utilizes all types of auxiliary data. As we train auxiliary source-pivot and pivot-target translation models, we initialize some parameters of the pivot side with a pre-trained language model and freeze them to encourage both translation models to work in the same pivot language space, so that they can be smoothly transferred to the source-target translation model. Experiments show that our approach can outperform previous ones.- Anthology ID:
- 2022.acl-short.72
- 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:
- 644–650
- Language:
- URL:
- https://aclanthology.org/2022.acl-short.72
- DOI:
- 10.18653/v1/2022.acl-short.72
- Cite (ACL):
- Meng Zhang, Liangyou Li, and Qun Liu. 2022. Triangular Transfer: Freezing the Pivot for Triangular Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 644–650, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Triangular Transfer: Freezing the Pivot for Triangular Machine Translation (Zhang et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-short.72.pdf