On Using Monolingual Corpora in Neural Machine Translation

TL;DR

This paper explores leveraging monolingual corpora to improve neural machine translation, demonstrating significant BLEU score gains across low-resource and high-resource language pairs.

Contribution

It introduces a method to incorporate monolingual data into neural machine translation, enhancing performance beyond traditional parallel data reliance.

Findings

Up to 1.96 BLEU improvement on Turkish-English

1.59 BLEU gain on Chinese-English chat translation

Additional improvements on Czech-English and German-English

Abstract

Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation. Arguably, one of the major factors behind this success has been the availability of high quality parallel corpora. In this work, we investigate how to leverage abundant monolingual corpora for neural machine translation. Compared to a phrase-based and hierarchical baseline, we obtain up to $1.96$ BLEU improvement on the low-resource language pair Turkish-English, and $1.59$ BLEU on the focused domain task of Chinese-English chat messages. While our method was initially targeted toward such tasks with less parallel data, we show that it also extends to high resource languages such as Cs-En and De-En where we obtain an improvement of $0.39$ and $0.47$ BLEU scores over the neural machine translation baselines, respectively.