Unsupervised Machine Translation Using Monolingual Corpora Only

Introduction

The paper presents an unsupervised method to machine translation using only monoligual corpora without any alignment between sentences or documents. Monoligual corpora are text corpora that is made up of one language only. This contrasts with the usual translation approach that uses parallel corpora, where two corpora are the direct translation of each other and the translations are aligned by words or sentences.

The general approach of the methodology is to first use a unsupervised word-by-word translation model proposed by [Conneau, 2017], then iteratively improve on the translation by utilize 2 architectures:

1. A denoising auto-encoder to deconstruct noisy versions of sentences for both source and target languages
2. A discriminator to align the distributions of the source and target languages in a latent space.

References

1. [Conneau, 2017] Conneau, Alexis, Guillaume Lample, Marc’Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou. "Word Translation without Parallel Data". arXiv:1710.04087