Effective Domain Mixing for Neural Machine Translation

Neural Machine Translation (NMT) models are often trained on heterogeneous mixtures of domains, from news to parliamentary proceedings, each with unique distributions and language. In this work we show that training NMT systems on naively mixed data can degrade performance versus models fit to each constituent domain. We demonstrate that this problem can be circumvented, and propose three models that do so by jointly learning domain discrimination and translation. We demonstrate the efficacy of these techniques by merging pairs of domains in three languages: Chinese, French, and Japanese. After training on composite data, each approach outperforms its domain-specific counterparts, with a model based on a discriminator network doing so most reliably. We obtain consistent performance improvements and an average increase of 1.1 BLEU.