Google Translate has got a big achievement in 10 recent years. When first being launched, it just supports for a few languages, now this figure is up to 103. Moreover, Google Translate also helps connecting strangers, reaching across language barriers. Today, Google continues to release a new update for Google Translate with better translation feature. That is Neural Machine Translation.
In basic terms, the Neural system allows Google to translate whole sentences at a time, rather than the previous method which can only translate word by word at a time. It uses this broader context to help it figure out the most relevant translation, then the translation will be rearranged and adjusted with better grammar to be more like a human speaking. So it’s easier for users to understand each sentence, translating paragraphs and even articles will also be smoother and easier to read. And this is all possible because a learning system has been built on Neural Machine Translation that means the system can learn over time to create better, more natural translations than before.
With this new update, Google Translate will use the new Neural Machine Translation methods on text and support for a total of eight languages English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish. These represent for the native languages of one-third of the world’s population, taking more than 35% of all Google Translate queries. Goggle claims that this is the biggest improvement ever for Google Translate in the past10 years. The ultimate goal for the Neural Machine Translation method is that it can extend to the over 100 languages that are now supported by Google Translate.
If you are using Google Translate, what are your impressions of the translations in the languages supported by the new machine learning method? Share your thoughts with us in the comment below