Popular mobile keyboard app SwiftKey is flexing its multilingual muscles today with the launch of a handful of new features for those able to converse in multiple languages.

You may recall that the Microsoft-owned company rolled out a significant upgrade to its Android app last month, one that beckoned a branch of machine learning called “neural networks” into the mix. In a nutshell, these neural networks are more closely based on the workings of the human brain, and, compared to the old n-gram model — which was more about computational linguistics and probability — are better at predicting and correcting language by considering the context of what someone is trying to say.

N-gram vs. Neural Networks

Above: N-gram vs. Neural Networks

So far, the new SwiftKey app has been limited to the English language (U.S. and U.K.), but now it’s also available in Spanish, French, and German, opening its new smarts to hundreds of millions more people around the world.

Moreover, the non-neural networks version of SwiftKey was already available in 125 tongues and let users switch between up to three languages at any given time. This was perhaps useful for someone who chats to their parents in their native lingo but their friends in English and French. Now SwiftKey has expanded this to five simultaneous languages.

AI Weekly

The must-read newsletter for AI and Big Data industry written by Khari Johnson, Kyle Wiggers, and Seth Colaner.

Included with VentureBeat Insider and VentureBeat VIP memberships.

Founded in 2008, SwiftKey built a big following on Android as an alternative to the stock bundled keyboard app, and it finally arrived on iOS after Apple opened to third-party keyboards. The company was acquired by Microsoft earlier this year, and cofounder and CTO Ben Medlock recently explained his reasons for selling.

VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Learn More