The internet has made the world feel smaller, connecting people all over Earth. The problem? Many of us speak different laguages! Sure, some of you speak multiple languages, but for many of us — including yours truly — one is all we know.
Thankfully, translation services — such as Google Translate — removes barriers, allowing people to more easily communicate despite language differences. Today, the search giant announces that it has massively improved its service thanks to Neural Machine Translation technology.
But wait, what is Neural Machine Translation, anyway? Barak Turovsky, Translate Product Lead, Google explains the following.
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. 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, which basically means that the system learns over time to create better, more natural translations.
Turovsky further says, “today we’re putting Neural Machine Translation into action with a total of eight languages to and from English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish. These represent the native languages of around one-third of the world’s population, covering more than 35 percent of all Google Translate queries”.
While many of Google Translate’s most popular langauges are supported by this technology, the search giant still has a long way to go. Still, as some people say, “don’t let perfect get in the way of better”. In other words, Google deserves kudos for improving the service — even if only a fraction of users will experience the benefits today.