Unsupervised Machine Translation Using Monolingual Corpora Only

TL;DR

This paper introduces an unsupervised machine translation model that learns to translate between languages using only monolingual data, achieving competitive results without any parallel training data.

Contribution

It presents a novel approach that maps monolingual sentences into a shared latent space, enabling translation without parallel corpora, a significant step for low-resource language translation.

Findings

Achieved BLEU scores of 32.8 and 15.1 on two datasets

Demonstrated effective translation without parallel data

Validated on multiple language pairs

Abstract

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource language pairs, yet requiring tens of thousands of parallel sentences. In this work, we take this research direction to the extreme and investigate whether it is possible to learn to translate even without any parallel data. We propose a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space. By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data. We demonstrate our model on two widely used datasets and two language pairs, reporting BLEU scores of 32.8 and 15.1 on the Multi30k and WMT English-French datasets, without using even a single parallel sentence at training time.