An incoming update to Google Translate on the web and mobile app will enhance the service's ability to translate whole sentences at a time, instead of going word by word. With the help of "Neural Machine Translation," Google said that Google Translate will be able to look at the "broader context" of a phrase to parse out a more naturalistic representation in the native language of the app's user.
With the update, Google mentioned that now translated paragraphs and entire articles are going to be "a lot smoother and easier to read," thanks to the new end-to-end learning system introduced within Neural Machine Translation. Like other AI-learning software, Google said this "basically means that the system learns over time to create better, more natural translations."
Neural Machine Translation has been generating exciting research results for a few years and in September, our researchers announced Google's version of this technique. At a high level, the Neural system translates whole sentences at a time, rather than just piece by piece. It uses this broader context to help it figure out the most relevant translation, which it then rearranges and adjusts to be more like a human speaking with proper grammar.
With this update, Google Translate is improving more in a single leap than we’ve seen in the last ten years combined.
Across Google Translate on the web and in its iOS and Android apps, users will be able to put Neural Machine Translation to the test with eight languages to and from English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish. The company plans to eventually roll the update out to all of its 103 supported languages, and any device Google Translate is available on.
Google Translate is available to download for free from the App Store [Direct Link]. Google didn't confirm when Neural Machine Translation would begin rolling out, besides the fact that it'll be coming to Google Search, the Google Translate app, and the official website first.