Unsupervised Machine Translation Using Monolingual Corpora Only

ICLR 2018 Guillaume Lample • Alexis Conneau • Ludovic Denoyer • Marc'Aurelio Ranzato

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. By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Machine Translation WMT2016 English-German Unsupervised S2S with attention BLEU score 9.64 # 5
Machine Translation WMT2016 German-English Unsupervised S2S with attention BLEU score 13.33 # 5