Google Translate now supports five new experimental alpha languages of the Indian sub-continent: Bengali, Gujarati, Kannada, Tamil and Telugu.
"In India and Bangladesh alone, more than 500 million people speak these five languages. Since 2009, we've launched a total of 11 alpha languages, bringing the current number of languages supported by Google Translate to 63," Google stated.
"You can expect translations for these new alpha languages to be less fluent and include many more untranslated words than some of our more mature languages--like Spanish or Chinese--which've much more of the web content that powers our statistical machine translation approach. Despite these challenges, we release alpha languages when we believe that they help people better access the multilingual web. If you notice incorrect or missing translations for any languages, you can send in your feedback to help google graduate new languages from alpha status (see the under this post). If you're a translator, you'll also be able to take advantage of our machine translated output when using the Google Translator Toolkit," Google said.
"Since each of these languages have their own unique scripts, we've enabled a transliterated input method for those of you without Indian language keyboards. For example, if you type in the word "nandri," it'll generate the Tamil word (see what it means). To see all these beautiful scripts in action, you'll need to install fonts* for each language.
On December 15th, 2010, Google had launched a new feature that provide an alternate translations for each phrase in the translated text. "Just click the translated phrase and you'll see a pop-up menu of possible alternates for that phrase, as well as the original phrase highlighted in your original text." Not only can these alternative translations give you a better understanding of a confusing translation, but they also allow you to help Google choose the best alternative when a mistake is made.
"By using this feature, you can help improve Google Translate. Selecting phrase-level alternatives gives us feedback that fits well within the our system's statistical models. We hope to incorporate this structured feedback into our system, improving translation quality over time," Google added.
For more information about how our system works, check out here.
[Source: Google Translate blog]