Abstract
We participated in the WMT 2018 shared news translation task in three language pairs: English-Estonian, English-Finnish, and English-Czech. Our main focus was the low-resource language pair of Estonian and English for which we utilized Finnish parallel data in a simple method. We first train a “parent model” for the high-resource language pair followed by adaptation on the related low-resource language pair. This approach brings a substantial performance boost over the baseline system trained only on Estonian-English parallel data. Our systems are based on the Transformer architecture. For the English to Czech translation, we have evaluated our last year models of hybrid phrase-based approach and neural machine translation mainly for comparison purposes.- Anthology ID:
- W18-6416
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 431–437
- Language:
- URL:
- https://aclanthology.org/W18-6416
- DOI:
- 10.18653/v1/W18-6416
- Cite (ACL):
- Tom Kocmi, Roman Sudarikov, and Ondřej Bojar. 2018. CUNI Submissions in WMT18. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 431–437, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- CUNI Submissions in WMT18 (Kocmi et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W18-6416.pdf
- Data
- WMT 2018