Abstract
In this work, we investigate methods for the challenging task of translating between low- resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between several Indo-European low-resource languages from the Germanic and Romance language families. In particular, we build two main classes of transfer-based systems to study how relatedness can benefit the translation performance. The primary system fine-tunes a model pre-trained on a related language pair and the contrastive system fine-tunes one pre-trained on an unrelated language pair. Our experiments show that although relatedness is not necessary for transfer learning to work, it does benefit model performance.- Anthology ID:
- 2021.wmt-1.41
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 347–353
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.41
- DOI:
- Cite (ACL):
- Wei-Rui Chen and Muhammad Abdul-Mageed. 2021. Machine Translation of Low-Resource Indo-European Languages. In Proceedings of the Sixth Conference on Machine Translation, pages 347–353, Online. Association for Computational Linguistics.
- Cite (Informal):
- Machine Translation of Low-Resource Indo-European Languages (Chen & Abdul-Mageed, WMT 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.wmt-1.41.pdf