All about Google’s MuRIL.
                     ALL ABOUT GOOGLE’S 
MURIL
INTRODUCTION
 Google is the technology giant that drives 
local languages in India and more people 
who are not English speakers in the world 
come online. 
Source: thenextweb.com
INDIAN CUSTOMER BASE
 India has added over 100 million new 
internet users from rural India in the last two 
years. 
 Every new user coming online is an Indian 
language user.
 Calling up the industry to take a Bharat-first 
approach and build an internet that works 
for every Indian.
Source: economictimes.com
MACHINE LEARNING TOOL
 Google has unveiled a machine learning tool 
for Indian languages to help researchers, 
students, and startups keen on building local 
language technologies with a common 
framework across several languages in the 
country.
Source: economictimes.com
MULTILINGUAL REPRESENTATIONS 
FOR INDIAN LANGUAGES (MURIL) 
 The Multilingual Representations for Indian 
Languages (MuRIL) aims at solving problems 
surrounding Indian computer systems' 
interpretation of the language and all their 
ambiguity, such as mixed languages and 
other instances in the Indian context. 
Source: inc42.com
PUPOSE OF MURIL MODEL
 The model's purpose is to resolve issues 
relating to Indian language understanding. 
 It also supports transliterated text such as 
writing Hindi using Roman script.
Source: jagranjosh.com
HIGHEST COVERAGE FOR INDIAN 
LANGUAGES
 MuRIL was founded at the research unit for 
Google in India and is currently supporting 
16 local languages and English that, among 
other common machine learning models of 
its kind, are the highest coverage for Indian 
languages. 
Source: economictimes.com
BERT MODEL
 The BERT model ("Bidirectional Encoder 
Representations from Transformers") of the 
business has been educated and is currently 
used to evaluate almost every English 
question on its search engine.
Source: economictimes.com
EVOLUTION FOR INDIAN LANGUAGE
 MuRIL is a starting point of what Google 
believe can be the next big evolution for 
Indian language understanding. 
 Google hope it will prove to be a better 
foundation for researchers, startups, 
students, and anyone else interested in 
building Indian language technologies.
Source: moneycontrol.com
COMMON FOUNDATION
 This model will reduce the amount of time 
required for researchers and startups to 
train machine learning models, by acting as 
a common foundation to transfer the 
knowledge and learning from one language 
model to another.
Source: bgrindia.com
FREE AND OPEN-SOURCE
 Google has made MuRIL free and open-
source, available for download and use from 
its machine learning platform TensorFlow. 
 They have trained the model entirely on 
publicly available data corpus in order to 
make it easier for researchers to reproduce 
the results.
Source: zdnet.com