Google has developed a new version of its Translate tool and according to the company, it's almost as good as human translation. The app, like many other computer-powered translation services, lets tourists or people abroad for business speak in their own language and then translates it into that of the country they're in. However, comically bad mistranslations are common and are seen as inevitably associated with automated translation. The new software Google is rolling out, which starts with a Mandarin to English version today, should change that. Google calls the new method Neural Machine Translation, says Quartz, and it is "radical" change from the previous system.

Google's latest advance in machine learning could make the world a little smaller. The company is reëngineering its translation service after Google researchers invented a system that is significantly more accurate. In a competition that pitted the new software against human translators, it came close to matching the fluency of humans for some languages, such as when translating from English to Spanish. Google has already begun rolling out the new system for translations from Chinese to English (see examples showing the improvement). The company expects to replace its current translation system altogether.

If you are translating text or speech, it seems obvious that you should read a whole sentence before figuring out what it means. But this hasn't been so easy for computers--in part because the work sucks up so many resources. So Google Translate has had to get by with looking at pieces of sentences, words, and phrases, and translating them individually. On Tuesday, Google announced a new system called Google Neural Machine Translation (GNMT) that works on whole sentences and improves accuracy about 60% on average over the old phrase-based machine translation (PBMT), including on notoriously difficult Chinese-to-English translations. This is the first translation to roll out to the Google Translate mobile and web apps, available now.

When Google launched Google Translate 10 years ago, the key algorithm behind the service was Phrase-Based Machine Translation. The translations provided by the service have since vastly improved due to the developments in machine intelligence, but the recent addition of neural networks has provided Google Translate with the biggest boost that it has ever received. Language is naturally phrase-based, which is why translating between languages is not as simple as plugging in the translation of words in sentences. While computers have been developed to handle phrase-based translation, there are still nuances in languages that the machines are not able to understand. Google has now deployed the Google Neural Machine Translation system, which utilizes machine learning and neural networks to provide a massive boost in translation accuracy.

Starting today, Google will rely more heavily on artificial intelligence when it translates language. The new method, called Google Machine Neural Translation, cuts down errors by 80 percent compared to its current algorithm, and is nearly indistinguishable from human translation on standardized tests, the company said. It's a radical change from how Google translates now, which is called phrase-based translation, and is standard for the industry. Under this method, an algorithm cuts up a sentence, like one entered by a high-schooler trying to game their homework, and attempts to match words or phrases to a large dictionary. The new method takes that same large dictionary and uses it to train two neural networks.

If you have ever tried to decipher a foreign document using Google Translate, you might be aware of that unique feeling of part-frustration, part-amusement that comes when there is clearly something wrong with the result. Although they are only ever small, mistranslations do creep in, altering the overall effectiveness of the translation tool. But Google is now hoping to fix this problem, using artificial intelligence. The Google Translate tool, which launched ten years ago, has now been updated to use a deep learning model known as neural machine translation. The Google Translate tool, which launched ten years ago, has now been updated to use a deep learning model known as neural machine translation.

Last March, a computer built by a team of Google engineers beat one of the world's top players at the ancient game of Go. The match between AlphaGo and Korean grandmaster Lee Sedol was so exhilarating, so upsetting, and so unexpectedly powerful, we turned it into a cover story for the magazine. On a Friday in late April, we were about an hour away from sending this story to the printer when I got an email. According to the email, Lee had won all five matches--and all against top competition--since his loss to AlphaGo. Even as it surpasses human talents, AI can also pull humans to new heights--a theme that ran through our magazine story.

Quoc Le is no stranger to the indignity of translation. Whenever the Google research scientist in Mountain View, California, visits his native Vietnam, he laughs with his parents over mistranslations in the very system he is helping shape, the 10-year-old online service Google Translate. Most errors are tiny--not important enough to remember. But together, they tell a larger story: "Translation is not a solved problem," he says. But that may all change soon.

While there is the paper, the blogpost is a fun read and usually more digestible.