Google unveils a machine learning tool for Indian languages to help users keen on building local language technologies through a common framework across multiple languages.
The model – Multilingual Representations for Indian Languages (MuRIL) – aims to address issues around Indian language understanding of computer systems and complexities like spelling variations, transliteration, mixed languages, and use cases concerning the Indian context. It also supports transliterated text, such as writing Hindi using Roman script.
MuRIL was developed at Google’s India research unit and currently supports English and 16 local languages. The tech giant says this is the highest coverage for Indian languages among other publicly available machine learning models of its kind.
To Read More: cio.economictimes