From Bilingual to Multilingual Neural Machine Translation by Incremental Training

Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa


Abstract
Multilingual Neural Machine Translation approaches are based on the use of task specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that allows the system to scale to more languages without modification of the previous components based on joint training and language-independent encoder/decoder modules allowing for zero-shot translation. This work in progress shows close results to state-of-the-art in the WMT task.
Anthology ID:
P19-2033
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
236–242
Language:
URL:
https://www.aclweb.org/anthology/P19-2033
DOI:
10.18653/v1/P19-2033
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-2033.pdf