Google Translate has now expanded to cover 13 new languages. The expansion means that Translate now covers 99% of the online population. It’s taken about a decade for Translate to cover such a high percentage of online users after opening in 2006 with translations between English, Arabic, Chinese, and Russian. The 13 new languages include Amharic, Corsican, Frisian, Kyrgyz, Hawaiian, Kurdish (Kurmanji), Luxembourgish, Samoan, Scots Gaelic, Shona, Sindhi, Pashto and Xhosa.
Google says that there are 120 million people around the world who speak these 13 new languages. Google talks a bit about what it takes to become a Google Translate supported language. The first criteria is that the language has to be a written language. Google also need a significant amount of translations in the language to be available on the web. Exactly how many constitutes a significant amount is unclear.
Once those criteria are met, Google then uses machine learning, licensed content, and the Translate Community. With those translation weapons at the ready, the machine learning identifies statistical patterns allowing the machines to learn the language. Google says that over 3 millon people have contributed around 200 million translated words to the mix.
Some of the languages that have been added with this update are not common and might not be languages many have heard of. Corsican for instance is from the Island of Corsica, France, is related to Italian, and was Napoleon’s first language according to Google. The addition of Luxembourgish completes the list of official EU languages that Translate supports. Scots Gaelic is from the Scottish highlands and was introduced by Irish settlers in the 4th century AD. Google plans to add more languages to Translate, it appears it wants support for all languages eventually.
SOURCE: Google Translate