Multi-way, multilingual neural machine translation

Orhan Firat, Kyunghyun Cho, Baskaran Sankaran, Fatos T. Yarman Vural, Yoshua Bengio

Research output: Contribution to journalArticlepeer-review


We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. We train the proposed multi-way, multilingual model on ten language pairs from WMT′15 simultaneously and observe clear performance improvements over models trained on only one language pair. We empirically evaluate the proposed model on low-resource language translation tasks. In particular, we observe that the proposed multilingual model outperforms strong conventional statistical machine translation systems on Turkish-English and Uzbek-English by incorporating the resources of other language pairs.

Original languageEnglish (US)
Pages (from-to)236-252
Number of pages17
JournalComputer Speech and Language
StatePublished - Sep 2017


  • Low resource translation
  • Multi-lingual
  • Neural machine translation

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Human-Computer Interaction


Dive into the research topics of 'Multi-way, multilingual neural machine translation'. Together they form a unique fingerprint.

Cite this