SwiftKey pledges more human-style predictions with 'neural network' keyboard capability

The latest edition of the SwiftKey Android app brings the feature, which has had a lengthy beta test, out to the masses.

swiftkey alpha
Credit: SwiftKey

SwiftKey has wrapped up its nearly year-long pilot of a “neural network” keyboard and is bringing it to the Android masses.

The company, now a Microsoft subsidiary, says that the new prediction model more closely aligns to the way that humans actually communicate. Several examples on the SwiftKey blog point to how the keyboard attempts to finish off sentences and phrases that are more likely to finish off your sentence in the way that you’d want. 

For example, SwiftKey will suggest finishing the sentence, “I’ll meet you at the...” with “office, hotel, or airport.” In the previous model, the choices would be “end, moment, or same.” Interestingly enough, when I tried that phrase with Google Keyboard, those were the exact three choices I got. 

SwiftKey first rolled this feature out last October in an alpha form, so you may have missed it if you didn’t want to roll the dice with your keyboard stability. However, a nearly year-long test run should ensure that most of the peskiest bugs have been squished.

The company says the neural network model will soon make its way over to the keyboard that it makes for iOS as well. If you want to give this a try and see if it can save you a few keystrokes, then grab the latest version of SwiftKey from the Play Store.

The impact on you: While our last judgment on the best Android keyboard gave the nod to Google Keyboard, it may be worth revisiting SwiftKey to see how this new system holds up. For such a test run, it’s usually best to go all-in with the app for a few days to see how it compares. Either way, the options for smart typing on Android are better than ever.

To comment on this article and other Greenbot content, visit our Facebook page or our Twitter feed.
Related:
Shop Tech Products at Amazon
Notice to our Readers
We're now using social media to take your comments and feedback. Learn more about this here.