Microsoft Research Lab develops Machine Translation tool for Gondi language
Published: August 14, 2020
Microsoft Research Lab, in collaboration with CGNet Swara, an Indian-voice based online portal, has launched an Interactive Neural Machine Translation tool, which translates sentences from Hindi and Gondi and vice-versa. CGNet Swara is an Indian voice-based online portal that gives people in the forests of central tribal India a platform for expression by reporting local news and stories through a phone call.
About Gondi Language
This is spoken by nearly 12 million Gond Adivasis and it is not standardized. There are different versions spoken in the six states in the country. Also, there is no written literature in the language and the dialects have passed down orally over the centuries. There are no local teachers of the language and ones coming from outside speak in Hindi only. This tool will strive towards making that issue a thing of the past.
About the Project by Microsoft
This project is an extension of the Microsoft Research Lab’s work on natural language processing technology and a part of that focuses on low-resource languages such as Gondi, where so little data is available. The team did this after getting to know about it from the Indian company involved in the project. Gondi has been chosen since it is a language widely spoken in six states in the country and that makes a substantial speaker base. The project has been implemented based on the suggestions from the community members themselves instead of the outsiders and technology experts.
Impact of the App
This application now has 35000 sentences and the objective is to have translations of at least 1 lakh sentences in the application. With this, a window will open up for the community as anything written in any major language can be translated into Gondi language. This will be made available on mobile also so that it can be accessed from anywhere, even in the low-internet areas of the state.
What is NLP?
NLP is known as that branch of artificial intelligence that enables the computer to understand human languages. The objective of the NLP is to read, understand and make sense of the human languages in a way that is valuable and can be utilized for something else.