Word Translation Without Parallel Data

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. read more

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Datasets


Introduced in the Paper:

MUSE

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Word Alignment en-es Adv - Refine - CSLS P@1 81.7 # 2
Word Alignment en-fr Adv - Refine - CSLS P@1 82.3 # 2
Word Alignment es-en Adv - Refine - CSLS P@1 83.3 # 2
Word Alignment fr-en Adv - Refine - CSLS P@1 82.1 # 2

Methods


No methods listed for this paper. Add relevant methods here