Domain Control for Neural Machine Translation
SYSTRAN International, Paris, France, Catherine Kobus, Josep Crego, Jean Sénellart · 2017
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 reestimated 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.