Every two weeks, a language is lost somewhere in the world due to a decline in the number of people who speak it.

Although mainstream Indian languages have a digital presence, MSR is focusing on low-resource languages.

English and seven other widely spoken languages, including Chinese and Spanish, dominate the internet. This means that 88% of the world’s languages are underrepresented on the internet. Around 1.2 billion people, or 20% of the world’s population, are unable to navigate the digital world using their native language.

Bo, a pre-Neolithic language of the Andaman Islands that are at least 65,000 years old, became extinct in 2010 when the last person who spoke it died.

Non-written languages, such as Idu Mishmi, spoken by a community of 11,000 people in Arunachal Pradesh, may be lost to future generations due to a lack of digital representation.

The Microsoft Research lab in India (MSR) launched a project in 2015 to create a digital presence for these low-resource languages.

MSR project ‘Ellora’

Project Ellora aims to preserve a language for posterity while also ensuring that communities that speak these languages can participate in the digital world.

“Ellora began when Microsoft Research India was looking at Indian languages and how it could get more data and techniques to build tech and applications for Indian languages”, explained Kalika Bali, principal researcher at Microsoft Research India and project leader.

Gondi, Mundari, and Idu Mishmi are the three Indian languages on which MSR has so far worked.

In collaboration with partner organizations, Microsoft Research identifies communities and builds a database of native speakers that will be utilized to develop AI solutions for those groups.

MSR worked with IIT-Kharagpur to do a study on what the community of one million Mundas, who dwell in portions of West Bengal, Odisha, and Jharkhand, requires in order to preserve the Mundari language.

MSR India is also collaborating with Microsoft Africa Research Institute to determine how this tool can be used in Africa.

Also read: National Film Heritage Mission Giving A New Lifeline To Indian Cinema: Anurag Thakur