Google Translate targets 5M Indic language speakers

At least five new languages from the Indian subcontinent have been added to Google’s language translation service, although on an “experimental" basis for now. Google research scientist Ashish Venugopal said Google Translate now supports the Bengali, Gujarati, Kannada, Tamil and Telugu languages. “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," Venugopal said in a blog post (http://googletranslate.blogspot.com/2011/06/google-translate-welcomes-you-to-indic.html). Venugopal said Indic languages differ from English in many ways, presenting several exciting challenges when developing their respective translation systems. According to Venugopal, Indian languages often use the Subject Object Verb (SOV) ordering to form sentences, unlike English, which uses Subject Verb Object (SVO) ordering. “This difference in sentence structure makes it harder to produce fluent translations; the more words that need to be reordered, the more chance there is to make mistakes when moving them. Tamil, Telugu and Kannada are also highly agglutinative, meaning a single word often includes affixes that represent additional meaning, like tense or number," Venugopal said. Venugopal said Google’s research to improve Japanese (an SOV language) translation helped it with the word order challenge, while its work translating languages like German, Turkish and Russian provided insight into the agglutination problem. “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 have much more of the web content that powers our statistical machine translation approach," Venugopal said. But despite these challenges, Venugopal said Google will release alpha languages when it believes that they help people better access the multilingual web. “If you notice incorrect or missing translations for any of our languages, please correct us; we enjoy learning from our mistakes and your feedback helps us graduate new languages from alpha status. If you’re a translator, you’ll also be able to take advantage of our machine translated output when using the Google Translator Toolkit," Venugopal said. Also, Google enabled a transliterated input method for those without Indian language keyboards. — TJD, GMA News