Reference Language based Unsupervised Neural Machine Translation

TL;DR

This paper introduces RUNMT, a novel reference language-based framework for unsupervised neural machine translation that leverages a shared parallel corpus with a reference language to enhance translation quality.

Contribution

It extends unsupervised NMT by incorporating a reference language with a parallel corpus, improving translation performance over single auxiliary language methods.

Findings

RUNMT outperforms baseline UNMT models using one auxiliary language.

The reference agreement mechanism effectively utilizes shared parallel corpora.

Experimental results demonstrate significant quality improvements in translation tasks.

Abstract

Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used pivot language in the absence of a source language to target language parallel corpus. The rise of unsupervised neural machine translation (UNMT) almost completely relieves the parallel corpus curse, though UNMT is still subject to unsatisfactory performance due to the vagueness of the clues available for its core back-translation training. Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community.