physicsphairy writes: Tomas Mikolov and others at Google have developed a simple means of translating between languages using a large corpus of sample texts. Rather than being defined by humans, words are characterized based on their relation to other words, e.g., in any language, a word like 'cat' will have a particular relationship to words like 'small', 'furry,' 'pet', etc. The set of relationships of words in a language can be described as a vector space, and words from one language can be translated into words in another language by identifying the mapping between their two vector spaces. The technique works even for very dissimilar languages, and is presently being used to refine and identify mistakes in existing translation dictionaries.
Attend or create a Slashdot 20th anniversary party! DEAL: For $25 - Add A Second Phone Number To Your Smartphone for life! Use promo code SLASHDOT25. Check out the new SourceForge HTML5 Internet speed test. ×