Phrase-Based & Neural Unsupervised Machine Translation

Guillaume LampleMyle OttAlexis ConneauLudovic DenoyerMarc'Aurelio Ranzato

   Papers with code   Abstract  PDF

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, 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... (read more)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.