Google Translate will be more accurate, thanks to machine learning


Sometimes the meaning is lost or you are just confused by the limited words automated translation has to offer. For those who use Google Translate, the experience is going to be less of a nightmare. The search giant is introducing machine learning to improve the quality of translation offered by the tool.

To enhance translation, Google said on Tuesday it is making use of ‘Neural Machine Translation’ that allows the tool to take entire sentences into consideration than just a single word at a time.

As of now, Neural Machine Translation is being implemented for translations to and from eight languages – English, French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish.

Soon, it will roll out the service to all of the 103 languages supported by the tool. For now only few languages are supported as Google says they represent the native languages of around one-third of the world’s population.

So how does it work? The Neural system uses broader context to help it figure out the most relevant translation. It then rearranges and adjusts with proper grammar. ” Since it’s easier to understand each sentence, translated paragraphs and articles are a lot smoother and easier to read. And this is all possible because of end-to-end learning system built on Neural Machine Translation,” writes Barak Turovsky, the product lead for Google Translate.

Barak said with this update Google Translate is improving more “in a single leap than we’ve seen in the last ten years combined”. It will be used in both web and mobile app of Translate.

Google also said it’s forming a Cloud Machine Learning group, which will focus on bringing its AI technology to other businesses.


Comments are closed.