Exploiting Similarities among Languages for Machine Translation

Abstract

Dictionaries and phrase tables are the basis of modern statistical machine translation systems. This paper develops a method that can automate the process of generating and extending dictionaries and phrase tables. Our method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data. It uses distributed representation of words and learns a linear mapping between vector spaces of languages. Despite its simplicity, our method is surprisingly effective: we can achieve almost 90% precision@5 for translation of words between English and Spanish. This method makes little assumption about the languages, so it can be used to extend and refine dictionaries and translation tables for any language pairs.

Extracted Key Phrases

11 Figures and Tables

05010015020132014201520162017
Citations per Year

389 Citations

Semantic Scholar estimates that this publication has 389 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Mikolov2013ExploitingSA, title={Exploiting Similarities among Languages for Machine Translation}, author={Tomas Mikolov and Quoc V. Le and Ilya Sutskever}, journal={CoRR}, year={2013}, volume={abs/1309.4168} }