comscore
News

Google Translate offline is set to get a boost with machine learning

Google Translate online version had machine learning integrated two years back.

  • Published: June 13, 2018 10:49 AM IST
Google_Translate_logo

Google has gone a long way in making our lives easier and this is evident from the fact that we use some of its products everyday in our lives. Google Translate is one of those products from the company that is boon for travelers going to places where they don’t speak the native language. Google Translate works just fine in terms of technicality, but there is always room for improvement.

Google made sure that people can access its Translate feature even in areas with patchy, or no network with the offline feature. And in a recent blog post Google declared that the offline services is about to get better with the integration of neural machine translation or NMT.

Google had already integrated NMT technology to online Google Translate two years ago which showed significant better results. And now Google is bringing NMT technology to Translate offline as well and will be integrating the technology on the device itself.

According to Google, “The neural system translates whole sentences at a time, rather than piece by piece. It uses broader context to help determine the most relevant translation, which it then rearranges and adjusts to sound more like a real person speaking with proper grammar. This makes translated paragraphs and articles a lot smoother and easier to read.”

Google Translate offline is a light app that only uses about 35-45MB for each language. To try NMT offline translations, users have to go to their Translate app on Android or iOS. For users that have used offline translations before, they will see a banner on the home screen that will take them to the update screen for the offline files. If not, users can go to their offline translation settings and tap the arrow next to the language name to download the package for that language.

Google is rolling out the update in 59 languages, and will be available over the next few days.

  • Published Date: June 13, 2018 10:49 AM IST