Tech gian Google has launched a machine learning tool for Indian languages to enable researchers, students, and startups to build local technologies in vernacular languages with a common framework, reports Economic Times.
The tool called Multilingual Representations for Indian Languages (MuRIL) has been developed by Google's India research unit, and it presently supports 16 languages and English. The tool aims to address concerns around Indian language understanding of computer systems, including all of its complexities like transliteration, spelling variations, mixed languages and other specific use cases which emerge in the Indian context.
Google claims that MuRIL offers the highest coverage for Indian languages among other such publically available models. Also, the tech major has made MuRIL free and open-source, making it available for download and use from its machine learning platform called TensorFlow.
Google has trained MuRIL tool using its existing language learning model called Bidirectional Encoder Representations from Transformers (BERT) which it uses to parse almost all the English queries on its search engine.
As per Partha Talukdar, a research scientist at Google India, MuRIL is a starting point of what the company believes can be the next big evolution for Indian language understanding.
As you are no doubt aware, Swarajya is a media product that is directly dependent on support from its readers in the form of subscriptions. We do not have the muscle and backing of a large media conglomerate nor are we playing for the large advertisement sweep-stake.
Our business model is you and your subscription. And in challenging times like these, we need your support now more than ever.
We deliver over 10 - 15 high quality articles with expert insights and views. From 7AM in the morning to 10PM late night we operate to ensure you, the reader, get to see what is just right.
Becoming a Patron or a subscriber for as little as Rs 1200/year is the best way you can support our efforts.