> http://www.regdeveloper.co.uk/2007/05/15/google_translation/ > > This is an article on statistical approaches to machine translation. > Has anyone attempted similar with computer go?
Thanks, that was a well-written article. I think when he says, "Statistics deals with ambiguity better than rules do, it turns out." he could've been talking about the monte carlo/UCT approaches to computer go. And while monte carlo may be the simplest way to write a 15-kyu program it has yet to be proved it is the best way to write a 6-dan program. Google translation is at the 15-kyu level and it isn't clear how far just throwing more computing power at the problem will get them. Incidentally, I think the Bleu approach to evaluating translation quality (i.e. a machine judging the quality of machine translation) is similar to judging improvements in our computer go programs with self-play: the results have to be taken with a grain of salt. And Google won the competition because they tuned their algorithms using Bleu. Darren -- Darren Cook http://dcook.org/mlsn/ (English-Japanese-German-Chinese free dictionary) http://dcook.org/work/ (About me and my work) http://dcook.org/work/charts/ (My flash charting demos) _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
