Soon, claims Microsoft

Aug 25, 2008 12:57 GMT  ·  By

Microsoft's Windows Live Translator is evolving and, in this context, new languages are just around the corner. According to Will Lewis, a program manager on the Microsoft Translator team, the Redmond company is ready to take out of the oven new pairs of translation systems, but failed to offer any deadline as to when the baking time will be over. Additionally, Lewis also proved shy of sharing details on the specific items which will be added to Windows Live Translator. The abstract "soon" was the sole indication given as to the proximity of the upcoming language releases.

"In the future, we plan to release new translation systems in pairs (with a couple of exceptions). I can't reveal what languages we have planned next, but do expect some new ones soon!" Lewis stated. The new language pairs will come on the heels of Microsoft bridging Windows Live Translator with the Office 2007 and Office 2003 systems. At the start of August 2008, the Redmond giant revealed that Office 2007 and Office 2003 users are now able to integrate Windows Live Translator with the two productivity suites.

Windows Live Translator was unveiled back in September 2007 as a Beta version and currently features no less than 25 language pairs. With the scarce details released by Microsoft the evolution of the service remains unknown outside of Redmond; however, the underlying Statistical Machine Translation (SMT) engine is being trained for additional languages.

"Statistical systems are different than rule-based ones in that the "rules" mapping words and phrases from one language to another are learned by the system rather than being hand-coded. Training an SMT requires amassing a large amount of parallel training data-hopefully of good quality and from heterogeneous sources-and training the engine on that data. (By parallel, we mean a source of data where the content for one language is the same as the content for the other)," added Lewis indicating that the engine would focus on the words and phrasal correspondences between texts in different languages.