Google Maps improves discoverability by rolling out automatic transliteration for Indian languages


Google is working on improving the discoverability factor Maps in India by adopting an ensemble of learning models that automatically transliterate certain points of interest (POIs) to 10 prominent local languages. Google Maps is of the opinion that this new feature will help users to issue queries in their own language and find information for the same in a comprehensible fashion. Be it tips on restaurants, petrol pumps, hospitals, grocery stores, banks, bus stops, or train stations, Maps will be able to use automatic transliteration to display their name in a known local language.


As per a press release by the firm, the transliteration will be carried out from the Latin script (English) name of a POI in any of the following Indian languages: Hindi, Bangla, Marathi, Telugu, Tamil, Gujarati, Kannada, Malayalam, Punjabi, and Odia. The language to which your query gets automatically transliterated into depends upon the language you have picked on Google Maps from the settings of the app.

Cibu Johny, a software engineer at Google Maps said, “Nearly three-quarters of Indians interact with the web primarily using local languages rather than English, and this number is only growing. To make Google Maps as helpful as possible for millions of Indian language users, we’ve introduced an updated automatic transliteration system that enables us to deliver more accurate results when users search for POIs in their preferred language”.

The engineer observed as our country has names of establishments written in multiple languages and acronyms, if they “phonetically” map these words into a native language, it will help Maps reach out to more users in India.

He explained how the feature would work. If the POI is NIT, Maps will now be able to understand that the acronym is pronounced as ‘en-aye-tee’ and not as the English word ‘nit’. Thus, the transliteration provided would correctly convert the pronunciation as well.

Google Maps has used several learned models, along with transliteration dictionaries and a module for acronyms to add names in local languages to millions of POIs across India, as per the company. They believe this feature has increased the quality and the coverage in some languages by nearly twenty-fold.

Times2 Desk
Latest News Headlines: Times2 covers Latest India News, Top Today's Breaking News on Business, India, World, Politics, Entertainment and Sports …