Answers are grounded in this paper and cite their sources.
Neural Machine Translation (NMT) performs poor on the low-resource language pair (X, Z), especially when Z is a rare language. By introducing another rich language Y , we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data (Y, Z) (may be small) and (X, Y ) (can be rich) to improve the translation performance of lowresource pairs. In this triangular architecture, Z is taken as the intermediate latent variable, and translation models of Z are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of (X, Y ). Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.
No takes yet. Share an insight, caveat, or question.
Ren et al. (2018) studied this question.