October 31, 2018
Phrase-Based & Neural Unsupervised Machine Translation
Empirical Methods in Natural Language Processing (EMNLP)
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of bitexts, which hinders their applicability to the majority of language pairs. This work investigates how to learn to translate when having access to only large monolingual corpora in each language. We propose two model variants, a neural and a phrase-based model.
By: Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato
Facebook AI Research
Natural Language Processing & Speech