Abstract
Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a “parent” model for a high-resource language pair and then continue the training on a low-resource pair only by replacing the training corpus. This “child” model performs significantly better than the baseline trained for low-resource pair only. We are the first to show this for targeting different languages, and we observe the improvements even for unrelated languages with different alphabets.- Anthology ID:
- W18-6325
- Volume:
- Proceedings of the Third Conference on Machine Translation: Research Papers
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 244–252
- Language:
- URL:
- https://aclanthology.org/W18-6325
- DOI:
- 10.18653/v1/W18-6325
- Cite (ACL):
- Tom Kocmi and Ondřej Bojar. 2018. Trivial Transfer Learning for Low-Resource Neural Machine Translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 244–252, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Trivial Transfer Learning for Low-Resource Neural Machine Translation (Kocmi & Bojar, WMT 2018)
- PDF:
- https://preview.aclanthology.org/author-url/W18-6325.pdf