Abstract
This paper describes CUNI submission to the WMT 2020 News Translation Shared Task for the low-resource scenario Inuktitut–English in both translation directions. Our system combines transfer learning from a Czech–English high-resource language pair and backtranslation. We notice surprising behaviour when using synthetic data, which can be possibly attributed to a narrow domain of training and test data. We are using the Transformer model in a constrained submission.- Anthology ID:
- 2020.wmt-1.14
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 171–174
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.14
- DOI:
- Cite (ACL):
- Tom Kocmi. 2020. CUNI Submission for the Inuktitut Language in WMT News 2020. In Proceedings of the Fifth Conference on Machine Translation, pages 171–174, Online. Association for Computational Linguistics.
- Cite (Informal):
- CUNI Submission for the Inuktitut Language in WMT News 2020 (Kocmi, WMT 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.14.pdf