PROMT Systems for WMT22 General Translation Task
Alexander Molchanov, Vladislav Kovalenko, Natalia Makhamalkina
Abstract
The PROMT systems are trained with the MarianNMT toolkit. All systems use the transformer-big configuration. We use BPE for text encoding, the vocabulary sizes vary from 24k to 32k for different language pairs. All systems are unconstrained. We use all data provided by the WMT organizers, all publicly available data and some private data. We participate in four directions: English-Russian, English-German and German-English, Ukrainian-English.- Anthology ID:
- 2022.wmt-1.28
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 342–345
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.28
- DOI:
- Cite (ACL):
- Alexander Molchanov, Vladislav Kovalenko, and Natalia Makhamalkina. 2022. PROMT Systems for WMT22 General Translation Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 342–345, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- PROMT Systems for WMT22 General Translation Task (Molchanov et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.wmt-1.28.pdf