Coming soon : (improved) Google Translator

At the recent web cast of the Google Factory Tour, researcher Franz Och presented the current state of the Google Machine Translation Systems. He compared translations of the current Google translator, and the status quo of the Google Research Lab's activities. The results were highly impressive. A sentence in Arabic which is now being translated to a nonsensical "Alpine white new presence tape registered for coffee confirms Laden" is now in the Research Labs being translated to "The White House Confirmed the Existence of a New Bin Laden Tape." ...

How do they do that? ... to the translation system, any language is treated the same, and there is no manually created rule-set of grammar, metaphors and such. Instead, the system is learning from existing human translations. Google relies on a large corpus of texts which are available in multiple languages.

This is the Rosetta Stone approach of translation ... all it needs is someone to feed the system the two books and to teach it the two are translations from language A to language B, and the translator can create what Franz Och called a "language model." I suspect it's crucial that the body of text is immensely large, or else the system in its task of translating would stumble upon too many unlearned phrases. Google used the United Nations Documents to train their machine, and all in all fed 200 billion words. This is brute force AI, if you want – it works on statistical learning theory only and has not much real "understanding" of anything but patterns ...

- So, when will this be rolled out? Will the biblical Tower of Babel thing happen again or is that passé already, with the successful completion of Taiwan's Taipei 101 ... :)

(2005-06-02 13:25:35 SGT) [Tech] Permalink

Comments:

Post a Comment:

Comments are closed for this entry.

« Case conversion in... | Main | Are CRTs History? »

Most popular blog postings on lowem.log :

1. Singapore SIBOR rate falls to 0.94% in Nov 2008, lowest since Jul 2004
2. Baltic Dry Index falls 93% as shipping rates plunge, signalling global economic collapse
3. Singapore SIBOR rate falls to 1.31%, lowest since Nov 2004
4. Singapore SIBOR interest rates fall to 1.5%, lowest since Dec 2004
5. Live spot gold price quotes chart on COMEX
6. 2010 Honda Civic Hybrid preliminary specifications released
7. Fuel prices seen stoking Malaysia inflation in 2008
8. How to insert currency exchange rates into Google Spreadsheets

Featured articles on lowem.log :

1. ABC Guide to Beating Inflation in Singapore and Elsewhere
2. Singapore inflation rate hits new 26-year high of 7.5% in Apr 2008
3. Baltic Dry Index falls 93% as shipping rates plunge, signalling global economic collapse
4. 67000 China factories closed in H1 2008 as global economic collapse takes hold
5. 2010 Honda Civic Hybrid preliminary specifications released
6. Peakoiler buys 2008 Honda Civic Hybrid FD3
7. NYMEX crude oil recovers from $32.40 low after 2.2 mbpd OPEC production cut announced
8. Singapore SIBOR rate falls to 0.94% in Nov 2008, lowest since Jul 2004