Multi-Domain Neural Machine Translation

2018/05/06 by Tars, Sander, Fishel, Mark · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1805.02282

Abstract

We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use multilingual NMT methods to create multi-domain translation systems, we show that this approach results in significant translation quality gains over fine-tuning. We also explore whether the knowledge of pre-specified text domains is necessary, turns out that it is after all, but also that when it is not known quite high translation quality can be reached.

Cited by

• Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach
• Optimal Corpus Aware Training for Neural Machine Translation

Related

• Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
• Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey
• Domain Control for Neural Machine Translation
• An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation