HackerPapers

arXiv:1309.4168cs.CL

Exploiting Similarities among Languages for Machine Translation

Tomas Mikolov, Quoc V. Le, Ilya Sutskever

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.

arXiv comments
Journal reference
DOI
Subjects
cs.CLComputation and Language

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from Oct 2013 to Mar 2017. Found in 1 HN submission from Aug 2015 to Aug 2015. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Facebook releases 300-dimensional pretrained Fasttext vectors for 90 languages 1 comment

    • Models are trained independently for each language. So unfortunately, you cannot directly compare words from different languages using these vectors. If you have a bilingual dictionary, you might try to learn a linear mapping from one language to the other (e.g. see…

      exgrvView on HNParent context

  2. Abstractions my Deep Learning word2vec model made 1 comment

    • I'm uncertain whether you mean the algorithm or the output. The question is interesting to both however. The most common method for producing word vectors, skip-grams with negative sampling, has been shown to be equivalent to implicitly factorizing a word-context matrix[1]. A…

      SmerityView on HNParent context

  3. Stanford researchers to open source model they say has nailed sentiment analysis 1 comment

    • Stanford Ph.D. student Richard Socher appreciates the work Google and others are doing to build neural networks that can understand human language. He just thinks his work is more useful ... "We’re actually able to put whole sentences and longer phrases into vector spaces…

      eadlamView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.