Google can now translate five Indian languages

Google has extended its translation services to five more Indian languages – Bengali, Gujarati, Kannada, Tamil and Telugu – besides Hindi potentially increasing its reach to over 500 million people.

“Beginning today, you can explore the linguistic diversity of the Indian sub-continent with Google translate, which now supports five new experimental alpha languages”, the internet search engine announced on the Google blog.

According to Google, more than 500 million people speak these five languages in India and Bangladesh alone. Having launched over 11 alpha languages since 2009, the current number of languages supported by Google Translate is around 63.

The translations for these five alpha languages are expected to be less fluent and might include many more untranslated words than languages like Spanish or Chinese, with more of web content that powers Google’s statistical machine translation approach.

“Indic languages differ from English in many ways, presenting several exciting challenges when developing their respective translation systems,” said Google research scientist Ashish 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,” he wrote.

As these languages have their own unique scripts, Google translate has enabled a transliterated input method for the users who do not have Indian language keyboards.

Google has also requested the users to improve the quality of the translations, by correcting errors and providing feedback.

Despite the challenges involved in the translation of Indian languages, Google feels it’s important to translate these languages in order to help people gain better access to the multilingual web, and encourage the publication of new content in Indic languages.

“We hope that the launch of these new alpha languages will help you better understand the Indic web and encourage the publication of new content in Indic languages, taking us five alpha steps closer to a web without language barriers,” Venugopal said.