AI summary

This paper introduces an approximate training algorithm based on importance sampling that allows the training of NMT models with larger target vocabulary. The results demonstrate improved translation performance and do not sacrifice speed for both training and decoding, achieving state-of-the-art results on the WMT'14 English→French translation task.

Abstract

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent success, neural machine translation has its limitation in handling a larger vocabulary, as training complexity as well as decoding complexity increase proportionally to the number of target words. In this paper, we propose a method based on importance sampling that allows us to use a very large target vocabulary without increasing training complexity. We show that decoding can be efficiently done even with the model having a very large target vocabulary by selecting only a small subset of the whole target vocabulary. The models trained by the proposed approach are empirically found to match, and in some cases outperform, the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models. Furthermore, when we use an ensemble of a few models with very large target vocabularies, we achieve performance comparable to the state of the art (measured by BLEU) on both the English→German and English→French translation tasks of WMT'14.