Abstract
This paper describes the PROMT submissions for the WMT 2019 Shared News Translation Task. This year we participated in two language pairs and in three directions: English-Russian, English-German and German-English. All our submissions are Marian-based neural systems. We use significantly more data compared to the last year. We also present our improved data filtering pipeline.- Anthology ID:
- W19-5331
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 302–307
- Language:
- URL:
- https://aclanthology.org/W19-5331
- DOI:
- 10.18653/v1/W19-5331
- Cite (ACL):
- Alexander Molchanov. 2019. PROMT Systems for WMT 2019 Shared Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 302–307, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- PROMT Systems for WMT 2019 Shared Translation Task (Molchanov, WMT 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/W19-5331.pdf