Comments on: Playing with Google Translate (still beta) http://sebastians-pamphlets.com/playing-with-google-translate-still-beta/ If you've read my articles somewhere on the Internet, expect something different here. Sat, 17 May 2008 03:28:18 +0000 http://wordpress.org/?v=2.2.3 By: Sebastian http://sebastians-pamphlets.com/playing-with-google-translate-still-beta/#comment-118 Sebastian Tue, 03 Jul 2007 09:07:00 +0000 http://sebastians-pamphlets.com/playing-with-google-translate-still-beta/#comment-118 Tony, thanks for the insight from an expert. I thought Franz Och's team developed the technology.

Tony, thanks for the insight from an expert. I thought Franz Och’s team developed the technology.

]]> By: Tony Ruscoe http://sebastians-pamphlets.com/playing-with-google-translate-still-beta/#comment-117 Tony Ruscoe Tue, 03 Jul 2007 08:37:00 +0000 http://sebastians-pamphlets.com/playing-with-google-translate-still-beta/#comment-117 <i>By the way, the quality of translated news, technical writings or academic papers is much better than rough translations of everyday language, so better don't try to get any sense out of translated forum posts and stuff like that. Probably that's caused by the lack of trusted translations of these sources which are necessary to train Google's algos.</i><br/><br/>It's worth noting that Google hasn't developed the technology behind any of their non-Beta language pairs; they simply use Systran.<br/><br/>And the reason why translations of technical writings and academic papers are more accurate is because Systran's rule-based translation engine obviously handles well-formed text better than text that's full of errors (like forum posts and comments, for example) because it follows these rules. By the way, the quality of translated news, technical writings or academic papers is much better than rough translations of everyday language, so better don’t try to get any sense out of translated forum posts and stuff like that. Probably that’s caused by the lack of trusted translations of these sources which are necessary to train Google’s algos.

It’s worth noting that Google hasn’t developed the technology behind any of their non-Beta language pairs; they simply use Systran.

And the reason why translations of technical writings and academic papers are more accurate is because Systran’s rule-based translation engine obviously handles well-formed text better than text that’s full of errors (like forum posts and comments, for example) because it follows these rules.

]]>