Google's AI can translate language pairs it has never seen

Google logoGoogle's AI is not just better at grasping languages like Mandarin, but can now translate between two languages it hasn't even trained on. In a research paper, Google reveals how it uses its own "interlingua" to internally represent phrases, regardless of the language. The resulting "zero-shot" deep learning lets it translate a language pair with "reasonable" accuracy, as long as it has translated them both into another common language.

The company recently switched its Translate feature to the deep-learning Google Neural Machine Translation (GNMT) system. That's an "end-to-end learning framework that learns from millions of examples," the company says, and has drastically improved translation quality. The problem is, Google Translate works with 103 languages, meaning there are 5,253 language "pairs" to be translated. If you multiply that by the millions of examples needed for training, it's insanely CPU intensive.

Google's AI can translate language pairs it has never seen

After training the system with several language pairs like English-to-Japanese and English-to-Korean, researchers wondered if they could translate a pair that the system hadn't learned yet. In other words, can the system do a "zero-shot" translation between Japanese and Korean? "Impressively, the answer is yes -- it can generate reasonable Korean to Japanese translations, even though it has never been taught to do so," Google says.

Even the researchers aren't 100 percent sure of how it works, because deep learning networks are notoriously difficult to understand. However, they were able to peek into a three-language model using a 3D representation of the internal data (above). When zooming in, the researchers noticed that the system automatically groups sentences with the same meanings from three different languages.

In essence, it developed its own "interlingua" internal representation for similar phrases or sentences. "This means the network must be encoding something about the semantics of the sentence rather than simply memorizing phrase-to-phrase translations," the researchers write. "We interpret this as a sign of existence of an interlingua in the network."

In one experiment, for instance, the team merged 12 language pairs into a model the same size as for a single pair. Despite the drastically reduced code base, they achieved "only slightly lower translation quality" than with a dedicated two-language model. "Our approach has been shown to work reliably in a Google-scale production setting and enables us to scale to a large number of languages quickly," the team says. Bear in mind that it only started seriously working on AI for languages a short time ago, so its rapid progress is pretty scary -- especially if you're a professional translator.

Source: Engadget

Tags: Google

Add comment

Your name:
Sign in with:
Your comment:

Enter code:

E-mail (not required)
E-mail will not be disclosed to the third party

Last news

Galaxy Note10 really is built around a 6.7-inch display
You may still be able to download your content
Facebook, Messenger and Instagram are all going away
Minimize apps to a floating, always-on-top bubble
Japan Display has been providing LCDs for the iPhone XR, the only LCD model in Apple’s 2018 line-up
The 2001 operating system has reached its lowest share level
The entire TSMC 5nm design infrastructure is available now from TSMC
The smartphone uses a Snapdragon 660 processor running Android 9 Pie
The Samsung Galaxy A5 (2017) Review
The evolution of the successful smartphone, now with a waterproof body and USB Type-C
February 7, 2017 / 2
Samsung Galaxy TabPro S - a tablet with the Windows-keyboard
The first Windows-tablet with the 12-inch display Super AMOLED
June 7, 2016 /
Keyboards for iOS
Ten iOS keyboards review
July 18, 2015 /
Samsung E1200 Mobile Phone Review
A cheap phone with a good screen
March 8, 2015 / 4
Creative Sound Blaster Z sound card review
Good sound for those who are not satisfied with the onboard solution
September 25, 2014 / 2
Samsung Galaxy Gear: Smartwatch at High Price
The first smartwatch from Samsung - almost a smartphone with a small body
December 19, 2013 /

News Archive



Do you use microSD card with your phone?
or leave your own version in comments (16)