During its I/O 2022 developer conference today, Google announced it is adding support for 24 new languages to its Translate tool, which now covers languages spoken by more than 300 million people, supporting a total of 133 languages.
“We are expanding Google Translate to include 24 under-resourced languages. For these languages, we created monolingual datasets by developing and using specialized neural language identification models combined with novel filtering approaches. The techniques we introduce supplement massively multilingual models with a self-supervised task to enable zero-resource translation.”
Newly added languages in Google Translate include Sanskrit, Tsongae, Sorani Kurdish, Assamese, and Dhivehi, among others. Google CEO Sundar Pichai also highlighted a new monolingual AI learning approach where Google’s translation algorithm learns how to translate a section of text without first seeing a sample.
Google noted that it would keep improving the technology so that it can deliver the same experience it does with languages like Spanish and German.
The complete list of new languages added to Google Translate can be found here.