Self-Supervised Neural Machine Translation

Dana Ruiter, Cristina España-Bonet, Josef van Genabith


Abstract
We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training.
Anthology ID:
P19-1178
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1828–1834
Language:
URL:
https://aclanthology.org/P19-1178
DOI:
10.18653/v1/P19-1178
Bibkey:
Cite (ACL):
Dana Ruiter, Cristina España-Bonet, and Josef van Genabith. 2019. Self-Supervised Neural Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1828–1834, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Self-Supervised Neural Machine Translation (Ruiter et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1178.pdf
Video:
 https://vimeo.com/384515284
Code
 ruitedk6/comparableNMT