At its I/O developer conference today, Google kicked things off by announcing an expansion relating to Google Translate. Namely, that the service now supports 24 additional languages. This brings the total supported languages to a whopping 133.
The new additions are the first where something called Zero-Shot Machine Translation was used – where a machine learning model only sees monolingual text. It learns to translate in another language without ever seeing a translation example. While technically impressive, this also means the level of translation accuracy is lower than for other languages, at least right now. Google says it will keep improving the results in the future.
The newly added languages are spoken by a total of over 300 million people across the globe, including 800,000 in the far northeast of India, and 45 million people in Central Africa. For the first time, some Indigenous languages of the Americas, as well as an English dialect have been added too.
The full list is: Assamese, Aymara, Bambara, Bhojpuri, Dhivehi, Dogri, Ewe, Guarani, Ilocano, Konkani, Krio, Kurdish (Sorani), Lingala, Luganda, Maithili, Meiteilon (Manipuri), Mizo, Oromo, Quechua, Sanskrit, Sepedi, Tigrinya, Tsonga, and Twi.