Triangular Transfer: Freezing the Pivot for Triangular Machine Translation

Meng Zhang, Liangyou Li, Qun Liu


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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2022.acl-short.72.pdf