Abstract
This paper describes the University of Tartu’s submission to the news translation shared task of WMT19, where the core idea was to train a single multilingual system to cover several language pairs of the shared task and submit its results. We only used the constrained data from the shared task. We describe our approach and its results and discuss the technical issues we faced.- Anthology ID:
- W19-5342
- 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:
- 382–385
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/W19-5342/
- DOI:
- 10.18653/v1/W19-5342
- Cite (ACL):
- Andre Tättar, Elizaveta Korotkova, and Mark Fishel. 2019. University of Tartu’s Multilingual Multi-domain WMT19 News Translation Shared Task Submission. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 382–385, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- University of Tartu’s Multilingual Multi-domain WMT19 News Translation Shared Task Submission (Tättar et al., WMT 2019)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/W19-5342.pdf