Google has announced a range of features to better understand Indian languages and help internet users use Google services in their native language. The search giant is making it easier to toggle Search results between English and four additional Indian languages: Tamil, Telugu, Bangla and Marathi.The team at Google Research India has announced a new machine learning model to help better understand human language. It is known as MuRIL (Multilingual Representations for Indian Languages). MuRIL currently supports 16 Indian languages as well as English.
Among many other benefits of this multilingual model that is specifically aimed at scaling across Indian languages, MuRIL also provides support for transliterated text such as when writing Hindi using Roman script, which was something missing from previous models of its kind.
One of the many tasks MuRIL is good at, is determining the sentiment of a sentence. For example, “Achha hua account bandh nahi hua” would previously be interpreted as having a negative meaning, but MuRIL correctly identifies this as a positive statement. Or take the ability to classify a person versus a place: ‘Shirdi ke sai baba’ would previously be interpreted as a place, which is wrong, but MuRIL correctly interprets it as a person.
MuRIL has been made an open source, and it is currently available to download from the TensorFlow Hub, for free. MuRIL will be the next big evolution for Indian language understanding, forming a better foundation for researchers, students, startups, and anyone else interested in building Indian language technologies.
In Google Maps, users can quickly change their Maps experience into one of nine Indian languages, by going to Settings, and tapping ‘App language’.