This is technical, but is now production on all Google translations services, even in Google Home, where I have been casually testing it. Phrases and words. Getting closer to a Babel fish? Quite a peek into something deep.
Zero-Shot Translation with Google’s Multilingual Neural Machine Translation System Posted by Mike Schuster (Google Brain Team), Melvin Johnson (Google Translate) and Nikhil Thorat (Google Brain Team) Google Research Blog.
In the last 10 years, Google Translate has grown from supporting just a few languages to 103, translating over 140 billion words every day. To make this possible, we needed to build and maintain many different systems in order to translate between any two languages, incurring significant computational cost. With neural networks reforming many fields, we were convinced we could raise the translation quality further, but doing so would mean rethinking the technology behind Google Translate.
In September, we announced that Google Translate is switching to a new system called Google Neural Machine Translation (GNMT), an end-to-end learning framework that learns from millions of examples, and provided significant improvements in translation quality. However, while switching to GNMT improved the quality for the languages we tested it on, scaling up to all the 103 supported languages presented a significant challenge ........
Finally, the described Multilingual Google Neural Machine Translation system is running in production today for all Google Translate users. Multilingual systems are currently used to serve 10 of the recently launched 16 language pairs, resulting in improved quality and a simplified production architecture. ... "