On Thu, Dec 22, 2011 at 8:03 PM, Colin Hercus <colinher...@gmail.com> wrote: > Hi Jed, > > Google have published some details of their algorithm and that's pretty much > how it works. > > If they want to do say English/Italian translation they find a lot of text > (books, menus etc.) that exist in both languages and then they analyse the > text counting words by frequency. This gives first mapping between words. > There's a lot more to it but frequency mapping is a key element. They must > have trained their system using some books where Rossi had been translated > to Smith. It's interesting that the computer learns to translate just by > analysis of these dual language texts and with very little human input or > language understanding. > > Colin
Interesting. I wonder if human-computers followed similar rules to translate the texts on the Rosetta stone. Harry
