Google has announced the addition of Sindhi as one of the 13 new languages its Translate tool will soon be able to support. This brings the total number of dialects it can convert to 103, with the company claiming this figure represents 99% of the world’s population.
The 13 new languages consist of Corsican, Kurdish (Kurmanji), Luxembourgish, Samoan, Xhosa, Amharic, Hawaiian, Sindhi, Scots Gaelic, Pashto, Kyrgyz, Shona, and Frisian. Google asserts all these combined cover over 120 million people across the world. Sindhi represents 26 million of them.
The company has been steadily increasing the number of Indian languages it supports, having added Malayalam to Google Translate back in December last year. The search giant is probably looking to tap into the growing number of first-time internet users in the country by making it easier for them to interact in their own tongue.
Sveta Kelman, the Senior Program Manager at Google Translate, says the introduction of Sindhi will help the new generation of speakers to increase their knowledge of the community. He also thinks it could be useful for English-speaking tourists who are unfamiliar with the language.
Also Read: Google says Indians are more conscious about online security now
In a blog post, Kelman talked about the requirements for a dialect to be added to Google Translate. First, it has to be a written language. Second, a significant chunk of translations in the tongue must be available online. The platform then uses a combination of machine learning, licensed content and the Translate community to begin the process.
The Google Translate Community has apparently seen 3 million members translating over 200 million words. Nearly 20000 people had contributed to over 1 million new Hindi translations in 2014. Sindhi and the other 12 languages will be rolled out in an update over the next few days.