Domain Control for Neural Machine Translation

Catherine Kobus, Josep Crego, Jean Senellart


Abstract
Machine translation systems are very sensitive to the domains they were trained on. Several domain adaptation techniques have already been deeply studied. We propose a new technique for neural machine translation (NMT) that we call domain control which is performed at runtime using a unique neural network covering multiple domains. The presented approach shows quality improvements when compared to dedicated domains translating on any of the covered domains and even on out-of-domain data. In addition, model parameters do not need to be re-estimated for each domain, making this effective to real use cases. Evaluation is carried out on English-to-French translation for two different testing scenarios. We first consider the case where an end-user performs translations on a known domain. Secondly, we consider the scenario where the domain is not known and predicted at the sentence level before translating. Results show consistent accuracy improvements for both conditions.
Anthology ID:
R17-1049
Volume:
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
Month:
September
Year:
2017
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
372–378
Language:
URL:
https://doi.org/10.26615/978-954-452-049-6_049
DOI:
10.26615/978-954-452-049-6_049
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://doi.org/10.26615/978-954-452-049-6_049