Domain Control for Neural Machine Translation

Abstract

Machine translation systems are very sensitive to the domains they were trained on. Several domain adaptation techniques have 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.

Published in RANLP 2017

References in corpus (4)

• Recurrent Neural Network Regularization
• Effective Approaches to Attention-based Neural Machine Translation
• Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
• Guided Alignment Training for Topic-Aware Neural Machine Translation

Cited by in corpus (9)

• CTRL: A Conditional Transformer Language Model for Controllable Generation
• A Survey of Domain Adaptation for Neural Machine Translation
• An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
• Neural Machine Translation Training in a Multi-Domain Scenario
• Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation
• Character-based NMT with Transformer
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
• Iterative Dual Domain Adaptation for Neural Machine Translation
• Continuous Space Reordering Models for Phrase-based MT