The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018

Miguel Graça, Yunsu Kim, Julian Schamper, Jiahui Geng, Hermann Ney


Abstract
This paper describes the unsupervised neural machine translation (NMT) systems of the RWTH Aachen University developed for the English ↔ German news translation task of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). Our work is based on iterative back-translation using a shared encoder-decoder NMT model. We extensively compare different vocabulary types, word embedding initialization schemes and optimization methods for our model. We also investigate gating and weight normalization for the word embedding layer.
Anthology ID:
W18-6409
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Venues:
EMNLP | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
377–385
Language:
URL:
https://www.aclweb.org/anthology/W18-6409
DOI:
10.18653/v1/W18-6409
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-6409.pdf