Abstract
This paper describes the PROMT submissions for the WMT 2018 Shared News Translation Task. This year we participated only in the English-Russian language pair. We built two primary neural networks-based systems: 1) a pure Marian-based neural system and 2) a hybrid system which incorporates OpenNMT-based neural post-editing component into our RBMT engine. We also submitted pure rule-based translation (RBMT) for contrast. We show competitive results with both primary submissions which significantly outperform the RBMT baseline.- Anthology ID:
- W18-6420
- 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:
- 456–460
- Language:
- URL:
- https://aclanthology.org/W18-6420
- DOI:
- 10.18653/v1/W18-6420
- Cite (ACL):
- Alexander Molchanov. 2018. PROMT Systems for WMT 2018 Shared Translation Task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 456–460, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- PROMT Systems for WMT 2018 Shared Translation Task (Molchanov, WMT 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-6420.pdf