Monday, June 19, 2006

Google Machine Translation System

Google gave journalists a glimpse of its next generation machine translation system at a May 19th Google Factory Tour. The system has been trained using the United Nations Documents as a corpus. This corpus is some 200 billion words worth of content. It uses existing source and target language translations (done by human translators at the U.N.) to find patterns it then uses to build rules for translating between those languages. Apparently it was successful where the current version had failed in translating certain phrases. If anyone were capable of making a serious go of MT, that would have to be Google..

Google has improved the algorithms for its MT program by feeding its computers the equivalent of 1 million books of text, using sources such as parallel translations of United Nations documents..

The results were very impressive, not the stupid machine translation you see on the Internet, which isn't really good..

Today, nearly every translation service offered on the Web - AOL, Alta Vista, Babblefish, even Google's - is powered by translation technology developed by Systran. The company, based in San Diego and Paris, has been involved in MT for more than 30 years. Each day, it translates more than 25 million Web pages..

The question is: what will they do with the new Google translator – where will they integrate it – and what side-effects would it have? If via Google we get our universal language, would that resolve many global problems by fostering cross-cultural understanding? Here is a speculative list of translation applications Google might implement; the key is auto-translation:
The Google Translation Service
The Google Browser
The Google Instant Messenger GIM
The Google Babelfish

-- Read More Here..
-- The machines do the translating [Google Blog]..
-- NIST 2005 Machine Translation Evaluation Official Results..
-- What is Machine Translation (MT)? [SYSTRAN Website]..

<.adjuster />

No comments:

Post a Comment