IIIT to break online language barrier.

HYDERABAD: The digital divide between Indian languages will be a thing of past soon as the International Institute of Information Technology (IIIT) Hyderabad, is all set to launch a machine translation system which enables the users to convert the content from one language to another.

To begin with, the IIIT is planning to launch a machine translation system for four pairs of Indian languages for internet users on March 30. Under the project named Sampark the system will enable users to convert the available content from Hindi to Punjabi, Punjabi to Hindi, Urdu to Hindi, and Telugu to Tamil.

“In fact, we are working on 18 pairs of languages. Four more pairs will be added in another 3-4 months and the entire set will be ready in about a year or so,” Rajeev Sangal, director, IIIT told TOI on Thursday.

Dipti Misra Sharma, project in-charge, said that the system translation from Punjabi to Hindi and Hindi to Punjabi has been worked out there are a few corners that are required to be smoothened in putting across the Hindi text into Urdu and Tamil into Telugu.

Another expert Rahmat Yousuf Zai, who is working on Urdu-Hindi and Hindi-Urdu translation, opined that there would be some problems of syntax or spelling in the beginning. “Urdu has more complex spelling system than Hindi. Therefore, when Urdu words are read by the machine it could misspell some of them. But all these could be sorted with feedback and suggestions from the users,” he added.

On shortlisting of 18 pairs of languages Sharma said, there are 122 languages spoken in India with 234 others described as mother tongues or dialects. Of these, the state has chosen 22 as scheduled languages that covers 96 per cent of population in the country. The combined population of Hindi and Urdu speakers is the fourth largest in the world, she said. The other major linguistic groups are Bengali, Telugu, Marathi and Tamil.

The machine translation of the first four pairs of languages will be launched by A P J Abdul Kalam, former President of India, during the opening of World Wide Web international conference in the city on March 30.

Source : TOI