Abstract
This paper describes the DFKI-NMT submission to the WMT19 News translation task. We participated in both English-to-German and German-to-English directions. We trained Transformer models and adopted various techniques for effectively training our models, including data selection, back-translation and in-domain fine-tuning. We give a detailed analysis of the performance of our system.- Anthology ID:
- W19-5350
- 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:
- 440–444
- Language:
- URL:
- https://aclanthology.org/W19-5350
- DOI:
- 10.18653/v1/W19-5350
- Cite (ACL):
- Jingyi Zhang and Josef van Genabith. 2019. DFKI-NMT Submission to the WMT19 News Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 440–444, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- DFKI-NMT Submission to the WMT19 News Translation Task (Zhang & van Genabith, WMT 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/W19-5350.pdf