NTT’s Neural Machine Translation Systems for WMT 2018

Makoto Morishita, Jun Suzuki, Masaaki Nagata


Abstract
This paper describes NTT’s neural machine translation systems submitted to the WMT 2018 English-German and German-English news translation tasks. Our submission has three main components: the Transformer model, corpus cleaning, and right-to-left n-best re-ranking techniques. Through our experiments, we identified two keys for improving accuracy: filtering noisy training sentences and right-to-left re-ranking. We also found that the Transformer model requires more training data than the RNN-based model, and the RNN-based model sometimes achieves better accuracy than the Transformer model when the corpus is small.
Anthology ID:
W18-6421
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:
461–466
Language:
URL:
https://aclanthology.org/W18-6421
DOI:
10.18653/v1/W18-6421
Bibkey:
Cite (ACL):
Makoto Morishita, Jun Suzuki, and Masaaki Nagata. 2018. NTT’s Neural Machine Translation Systems for WMT 2018. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 461–466, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
NTT’s Neural Machine Translation Systems for WMT 2018 (Morishita et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6421.pdf
Data
WMT 2018