Google Translate is getting really, really accurate

Google Translate was rated an average of 4.3 while human translators got 4.6. in Chinese/English translation using the new system.

Any students using Google Translate to cheat on their Spanish homework can rejoice. The foreign-language translation tool is about to get a whole lot more accurate.

Last week, Google launched an updated translation tool that utilizes sophisticated artificial intelligence to produce startlingly accurate language translations.

While the tool has been used to successfully translate between English and Spanish, French and Chinese in a research setting, it's only available currently to everyday users for Chinese to English translations. The new system, which uses deep machine learning to mimic the functioning of a human brain, is called the Google Neural Machine Translation system, or GNMT.

To test the system, Google had human raters evaluate translations on a scale from 0 to 6. Translating from English to Spanish, the new Google tool's translation was rated an average of 5.43; human translators earned an average of 5.5.

For Chinese to English, the only public-facing option that currently utilizes the new system, Google Translate was rated an average of 4.3 while human translators got 4.6.

Overall, across all three languages, Google said its new tool is 60 percent more accurate than the old Google Translate tool, which used phrase-based machine translation, or PBMT.

"With the previous PBMT model, when we translate a sentence from one language to another, we would translate one word or a phrase in the source sentence at a time, then re-order the words in the correct grammar of the target language," said Quoc Le, a Google researcher who worked on the project.

"The complication is language has a lot of ambiguity. In our new GNMT system, we treat a whole sentence as a unit, and translate [the words] in a group."

The complexity of a translation machine that can digest entire phrases rather than rely on word-by-word translation are somewhat lost even on the researchers themselves. In an interview with MIT Technology review, Le called the new translator "unsettling. But we've tested it in a lot of places and it just works."

We hope this research increases the ability for people around the world to communicate with others regardless of what languages they speak.

Quoc Le, Google researcher

Despite its improved accuracy, the GNMT model still mistranslates rare terms and occasionally drops words. And it hasn't acquired any common sense. Given the sentence "the trophy cannot fit the cabinet because it's too big," the model could mistranslate because it doesn't know which "it" is the one that's too big. "GNMT doesn't have a model of the how the world actually works yet," said Le.

While the tool is only being offered for one language pair now, Google said it plans to roll out the new system to more of the 10,000 language pairs that Google Translate currently supports. "We hope this research increases the ability for people around the world to communicate with others regardless of what languages they speak," said Le.