Abstract
We investigate ways of using monolingual data in both the source and target languages for improving low-resource machine translation. As a case study, we experiment with translation from Finnish to Northern Sámi.Our experiments show that while conventional backtranslation remains a strong contender, using synthetic target-side data when training backtranslation models can be helpful as well.We also show that monolingual data can be used to train a language model which can act as a regularizer without any augmentation of parallel data.- Anthology ID:
- 2024.findings-acl.768
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12949–12956
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.768
- DOI:
- Cite (ACL):
- Jonne Sälevä and Constantine Lignos. 2024. Language Model Priors and Data Augmentation Strategies for Low-resource Machine Translation: A Case Study Using Finnish to Northern Sámi. In Findings of the Association for Computational Linguistics ACL 2024, pages 12949–12956, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Language Model Priors and Data Augmentation Strategies for Low-resource Machine Translation: A Case Study Using Finnish to Northern Sámi (Sälevä & Lignos, Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.768.pdf