fbpx

This new tool from Google will help startups, researchers, others understand Indian languages better

The model aims to assist computer systems to understand as many as 16 different Indian languages to resolve linguistic complexities involved in translation, transliteration, and understanding the sentiment of what the user meant in his/her search.

Google, Google News, Google updates, Google officials, Meenakshi Lekhi, Personal Data Protection Bill 2019, Ola, Uber, Facebook, Twitter, Amazon, China, Google data, Google content, Google computer program
Google also announced the launch of the latest features for its users like easily toggling between search leads to English and Tamil, Telugu, Bangla, Marathi. (Reuters file photo)
Search engine Google, which has been performing on localizing the net profit Indians in their native languages and dialects, is now looking to assist startups, researchers, et al. who could be acting on building Indian language technologies (LT). LT is related to the computational processing of the written or a spoken variety of a language and geared toward easing its interaction with computer systems and processing an outsized amount of textual information.

Towards this, Google announced a multilingual model, on Thursday, called Multilingual Representations for Indian Languages (MuRIL). The model aims to assist computer systems to understand as many as 16 different Indian languages to unravel for linguistic complexities involved in translation, transliteration, and understanding the sentiment of what the user meant in his/her search.

For example, “the sentence 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 flexibility to classify someone versus an area: Shirdi ke sai baba would previously be interpreted as a place, which is wrong, but MuRIL correctly interprets it as someone,” the corporate said in a very blog post.

The free open-source MuRIL is currently available to download from the TensorFlow Hub. Google hoped it to be “the next big evolution for Indian language understanding, forming a stronger foundation for researchers, students, startups, and anyone else curious about building Indian language technologies.” The model also supports transliterated text like when writing Hindi using Roman script, which Google said was missing from previous models of its kind. Also, the support to 16 languages is that the “highest coverage for Indian languages among the other publicly available model of its kind.”

Google also announced the launch of latest features for its users like easily toggling between search leads to English and Tamil, Telugu, Bangla, Marathi other than Hindi; showing relevant content in Indian languages including Hindi, Bangla, Marathi, Tamil, and Telugu whether or not the user type query English; allowing users to use Google Maps into one in all nine Indian languages; and more.

The Indian language internet user base is probably going to grow at a CAGR of 18 percent to succeed in 536 million by 2021 vis-à-vis nation internet user base growing at 3 percent to achieve 199 million. Indian language internet users are expected to account for near 75 percent of the country’s internet user base by 2021, in line with a 2017 KPMG report. the expansion is going to be on the rear of penetration of internet-enabled devices, affordable high-speed internet, rising digital literacy, and more. a number of the Indian startups working leveraging language processing, speech recognition, conversational AI are Reverie Language Technologies, Niki.ai, Gnani.ai, Manthan, and more

top