Abstract
We describe the work of Johns Hopkins University for the shared task of news translation organized by the Fourth Conference on Machine Translation (2019). We submitted systems for both directions of the English-German language pair. The systems combine multiple techniques – sampling, filtering, iterative backtranslation, and continued training – previously used to improve performance of neural machine translation models. At submission time, we achieve a BLEU score of 38.1 for De-En and 42.5 for En-De translation directions on newstest2019. Post-submission, the score is 38.4 for De-En and 42.8 for En-De. Various experiments conducted in the process are also described.- Anthology ID:
- W19-5329
- 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:
- 287–293
- Language:
- URL:
- https://aclanthology.org/W19-5329
- DOI:
- 10.18653/v1/W19-5329
- Cite (ACL):
- Kelly Marchisio, Yash Kumar Lal, and Philipp Koehn. 2019. Johns Hopkins University Submission for WMT News Translation Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 287–293, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Johns Hopkins University Submission for WMT News Translation Task (Marchisio et al., WMT 2019)
- PDF:
- https://preview.aclanthology.org/landing_page/W19-5329.pdf