Abstract
We describe here the experiments we did for the the news translation shared task of WMT 2019. We focused on the new German-to-French language direction, and mostly used current standard approaches to develop a Neural Machine Translation system. We make use of the Tensor2Tensor implementation of the Transformer model. After carefully cleaning the data and noting the importance of the good use of recent monolingual data for the task, we obtain our final result by combining the output of a diverse set of trained models through the use of their “checkpoint agreement”.- Anthology ID:
- W19-5312
- 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:
- 163–167
- Language:
- URL:
- https://aclanthology.org/W19-5312
- DOI:
- 10.18653/v1/W19-5312
- Cite (ACL):
- Fabien Cromieres and Sadao Kurohashi. 2019. Kyoto University Participation to the WMT 2019 News Shared Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 163–167, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Kyoto University Participation to the WMT 2019 News Shared Task (Cromieres & Kurohashi, WMT 2019)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/W19-5312.pdf