Language Model-Driven Unsupervised Neural Machine Translation
This addresses the challenge of improving translation quality in unsupervised settings, which is incremental as it builds on existing back-translation methods.
The paper tackled the problem of noise and errors in synthetic data for unsupervised neural machine translation by using a language model to drive the system, resulting in outperforming prior systems by over 3 BLEU points on WMT tasks.
Unsupervised neural machine translation(NMT) is associated with noise and errors in synthetic data when executing vanilla back-translations. Here, we explicitly exploits language model(LM) to drive construction of an unsupervised NMT system. This features two steps. First, we initialize NMT models using synthetic data generated via temporary statistical machine translation(SMT). Second, unlike vanilla back-translation, we formulate a weight function, that scores synthetic data at each step of subsequent iterative training; this allows unsupervised training to an improved outcome. We present the detailed mathematical construction of our method. Experimental WMT2014 English-French, and WMT2016 English-German and English-Russian translation tasks revealed that our method outperforms the best prior systems by more than 3 BLEU points.