Skip to main content

Google is tackling fat fingers, text translation through Gboard's AI

google gboard go news
Malarie Gokey/Digital Trends
Gboard, Google’s mobile keyboard for iOS and Android, is almost like a digital secretary. It can predict what you’re going to type before you type it, perform Google searches, translates in real time between more than 15 different languages, and boasts a growing library of handy emojis. And on Thursday, Google researchers pulled back the curtain on efforts to make it better.

“Most people spend a significant amount of time each day using mobile-device keyboards: Composing emails, texting, engaging in social media, and more. Yet, mobile keyboards are still cumbersome to handle,” Google said. “The average user is roughly 35 percent slower typing on a mobile device than on a physical keyboard. To change that, we recently provided many exciting improvements to Gboard for Android, working towards our vision of creating an intelligent mechanism that enables faster input while offering suggestions and correcting mistakes, in any language you choose.”

In a post on the Google Research Blog, Google explained how Gboard is using machine learning to cut down on errors. Using neural networks — computer systems modeled on the human brain and nervous system — researchers were able to correct for for mistyped letters, misspellings, character insertions, and deletions. “[Gboard] address[es] these errors at the character level, mapping the touch points on the screen to actual keys,” Google said.

In addition, Google employed TensorFlow, its hardware-accelerated machine learning platform, to train hundreds of neural networks and optimize them for suggestions, completions, and other keyboard-specific features. After a year of work, the models were six times faster and 10 times smaller than the initial versions, Google said, and showed a 15 percent reduction in bad autocorrects and 10 percent reduction in “wrongly decoded gestures.”

Those changes were just the beginning. Google factored lexicon, which tells which words occur in a language, and probabilistic grammar, which tells what words are likely to follow other words, into Gboard’s machine intelligence. The result was what Google calls Finite-State Transducers, which power the app’s natural language processing and supply word completions and predictions.

Google used the same Finite-State Transducers to map sequences of Latin keys to symbol sequences in Indic languages. The result? Gboard lets you type a word according to its phonetic pronunciation — the Hindi “daanth” for “दांत” (teeth) — and automatically transliterates it. Compared to Gboard’s old system, the new models are 50 percent faster, and reduce the fraction of words users have to manually correct by more than 10 percent. “Some languages have multiple writing systems […] so between transliterated and native layouts, we built 57 new input methods in just a few months,” Google said.

“While we hope that these recent changes improve your typing experience, we recognize that on-device typing is by no means solved. Gboard can still make suggestions that seem nonintuitive or of low utility and gestures can still be decoded to words a human would never pick, Google said. “However, our shift towards powerful, machine-intelligence algorithms has opened new spaces that we’re actively exploring to make more useful tools and products for our users worldwide.”

Editors' Recommendations

Kyle Wiggers
Former Digital Trends Contributor
Kyle Wiggers is a writer, Web designer, and podcaster with an acute interest in all things tech. When not reviewing gadgets…
Get ready to waste your day with this creepily accurate text-generating A.I.
ai spots writing by fake news feature

Whether you believe it was one of the most dangerous versions of artificial intelligence created or dismiss it as a massive unnecessary PR exercise, there’s no doubt that the GPT-2 algorithm created by research lab OpenA.I. caused a lot of buzz when it was announced earlier this year.

Revealed in February, OpenA.I. said it developed an algorithm too dangerous to release to the general public. Although only a text generator, GPT-2 supposedly generated text so crazily humanlike that it could convince people that they were reading a real text written by an actual person. To use it, all a user had to do would be to feed in the start of the document, and then let the A.I. take over to complete it. Give it the opening of a newspaper story, and it would even manufacture fictitious “quotes.” Predictably, news media went into overdrive describing this as the terrifying new face of fake news. And for potentially good reason.

Read more
What is Google Duplex? The smartest chatbot ever, explained
Human-sounding Google Duplex arrives on wide range of devices in the U.S.
google duplex hands on io2018 2835

The world's introduction to Google Duplex -- technology both impressive and a bit on the creepy side -- featured a human-sounding robot having a conversation with a person who couldn't even tell that they were talking to a robot. The demo during Google I/O 2018 freaked some people out, but it impressed our Mobile editor, Julian Chokkattu, who got a chance to try out Duplex recently.

Google Duplex is a big leap in the evolution of artificial intelligence (A.I.). No, it won't lead to human-like robots that can do the laundry or go shopping like in the movie I, Robot (at least not anytime soon). But Google Duplex is a huge step in terms of A.I.’s ability to more naturally converse with humans. But what is it exactly?
When is Google Duplex coming out?
In October 2018, Google announced that Duplex functionality would start rolling out to Pixel phones in November 2019 on a city-by-city basis, starting with New York City. Now, however, the company has noted that the tech is far more available. In a blog post, the company announced that Duplex is available on all Pixel phones in as many as 43 U.S. states. Now, Duplex has grown beyond the confines of Google's Pixel range, and as of April 2019, you can now use Google Duplex on a wide range of Android and iOS devices in the U.S.

Read more
The OnePlus Watch 2 is the Wear OS smartwatch I’ve been waiting for
Person wearing OnePlus Watch 2 with a green strap on their left wrist.

The OnePlus Watch 2 -- the company's first Wear OS watch -- has entered a market that Samsung dominates. However, OnePlus' popularity as a smartphone brand can be expected to bring small, yet meaningful changes that benefit not only OnePlus users, but all of the Wear OS segment in general.

For almost a decade, Samsung and Apple have predominantly been the default options if you want a smartwatch that is actually useful and goes beyond flashy features. With Samsung shifting gears and migrating from its own Tizen OS to the (relatively) more universal Wear OS platform and Google releasing its own Pixel Watch after struggling with an identity crisis in the smartwatch world, the platform has much more traction than it did a few years ago. As OnePlus carves its way into the segment, it has the opportunity to entice people who don't wish to live within Samsung's limitations when using a Galaxy Watch with another brand's phone.

Read more