Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation

TL;DR

This paper demonstrates that combining monolingual data with self-supervision significantly enhances multilingual neural machine translation, especially for low-resource languages and zero-shot translation, enabling effective addition of new languages without parallel data.

Contribution

It introduces a method that leverages monolingual data with self-supervision to improve multilingual NMT, particularly for low-resource and zero-shot translation scenarios.

Findings

Monolingual data boosts low-resource language translation quality.

Self-supervision improves zero-shot translation performance.

Achieves up to 33 BLEU on ro-en translation without parallel data.

Abstract

Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via multilingual NMT. The second direction employs monolingual data with self-supervision to pre-train translation models, followed by fine-tuning on small amounts of supervised data. In this work, we join these two lines of research and demonstrate the efficacy of monolingual data with self-supervision in multilingual NMT. We offer three major results: (i) Using monolingual data significantly boosts the translation quality of low-resource languages in multilingual models. (ii) Self-supervision improves zero-shot translation quality in multilingual models. (iii) Leveraging monolingual data with self-supervision provides a viable path towards adding new languages to multilingual models, getting up to 33 BLEU on ro-en translation without any parallel data or back-translation.