The LMU Munich Unsupervised Machine Translation Systems

Dario Stojanovski, Viktor Hangya, Matthias Huck, Alexander Fraser


Abstract
We describe LMU Munich’s unsupervised machine translation systems for English↔German translation. These systems were used to participate in the WMT18 news translation shared task and more specifically, for the unsupervised learning sub-track. The systems are trained on English and German monolingual data only and exploit and combine previously proposed techniques such as using word-by-word translated data based on bilingual word embeddings, denoising and on-the-fly backtranslation.
Anthology ID:
W18-6428
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
513–521
Language:
URL:
https://aclanthology.org/W18-6428
DOI:
10.18653/v1/W18-6428
Bibkey:
Cite (ACL):
Dario Stojanovski, Viktor Hangya, Matthias Huck, and Alexander Fraser. 2018. The LMU Munich Unsupervised Machine Translation Systems. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 513–521, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
The LMU Munich Unsupervised Machine Translation Systems (Stojanovski et al., WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6428.pdf