Google Translate Will Now Use Neural Learning To Make Even Better Translations

Google Translate Will Now Use Neural Learning To Make Even Better Translations
Facebook may have decided that you shouldn’t see the news, but we think you deserve to be in the know with Lifehacker Australia’s content. To sign up for our daily newsletter covering the latest news, hacks and reviews, head HERE. For a running feed of all our stories, follow us on Twitter HERE. Or you can bookmark the Lifehacker Australia homepage to visit whenever you need a fix.

If you need to translate some text, Google Translate will usually get you in the ballpark, but it’s not perfect. Now, the company hopes to vastly improve its translations with neural learning.

Google first announced it was researching ways to use neural networks to teach its computers how to get better at translating back in September. Now, the results of that program are being put into production. A new update to the Translate app will improve the translations to and from the following languages:

  • English
  • French
  • German
  • Spanish
  • Portuguese
  • Chinese
  • Japanese
  • Korean
  • Turkish

That’s a very small section of the languages Translate can already handle, but it also accounts for a large percentage of the spoken languages on Earth. The goal is for neural learning to help Translate understand the broader context of what’s being translated, rather than focusing on single words or phrases and missing grammar.

Found in translation: More accurate, fluent sentences in Google Translate [Google via Android Police]


Comments are closed.

Log in to comment on this story!