Word translation without parallel data

Guillaume Lample, Alexis Conneau, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

Feb 15, 2018 (modified: Feb 21, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.
  • TL;DR: Aligning languages without the Rosetta Stone: with no parallel data, we construct bilingual dictionaries using adversarial training, cross-domain local scaling, and an accurate proxy criterion for cross-validation.
  • Keywords: unsupervised learning, machine translation, multilingual embeddings, parallel dictionary induction, adversarial training