Skip to Content

Smartphone Dictionaries Go Gangnam Style

Swype’s Living Language feature adds slang to its auto-complete dictionary by watching what users type.
January 9, 2013

On the surface, the crowdfunding website Kickstarter, Indianapolis Colts coach Chuck Pagano, and Fukubukuro—a Japanese New Year’s custom whereby merchants sell grab bags of goods—seem completely unrelated.

As it happens, “Crowdfunding,” “Pagano,” and “Fukubukuro” are among the most popular new terms being typed by users of Swype’s predictive typing smartphone app. And a new crowdsourced feature, Living Language, allows users to contribute such words to a shared collaborative dictionary. This promises to make typing easier, and awkward auto-complete errors less common.

Swype lets users type by sliding a single finger around an on-screen keyboard.

Living Language, announced this week by Swype’s parent, Nuance Communications, makes it easier for users to type a phrase like “Gangnam Style” just by writing the “Gangnam” portion. It may also eventually enable Swype to roll out customized dictionaries based on a user’s geographical region or occupation, and add support for smaller languages that are often ignored by technology companies.

Swype already gives users the ability to add their own words to a built-in dictionary to improve its understanding of what they are trying to type. But, as Aaron Sheedy, vice president of text input for Nuance Mobile, notes, language varies tremendously from person to person and place to place, and it’s hard to keep up with constantly changing jargon and slang—not to mention doing so in many different languages.

That’s where Swype Living Language comes in. For those who activate the feature, Swype will periodically sync any new words you’ve added to your Swype user dictionary with the company’s database. If Swype sees a critical mass of people adding a word or phrase—such as “MakerBot”—it will push that out to participating users, Sheedy says. Right now, Swype is adding new words weekly.

Swype is also trolling popular blogs and websites for new words that can also be added to its collection. This only goes so far, though, as terms like “Gangnam Style” can show up in users’ vernacular well before becoming popular in the media, Sheedy says.

“Language is evolving ever more quickly, and it’s hard to keep up unless you’re asking for the permission to watch the way people are using language,” he says.

Living Language builds on an update Swype rolled out in September that allowed users to back up and sync their personal dictionaries—previously, you’d have to start all over again with the software when switching from one device to another.

When Swype rolled out that update, the company asked some users if they could poke around in their data, Sheedy says, and noticed tens of thousands of appearances of the word “Lochte”—referring to Olympic swimmer Ryan Lochte. This helped the team realize that people need to have very up-to-date dictionaries that include subjects trending in the world around us.

Jim Glass, a senior research scientist at the MIT Computer Science and Artificial Intelligence Laboratory who heads the lab’s spoken language systems group, says that Living Language doesn’t really cost the company or its users anything but should ultimately benefit both.

“As soon as companies produce a dictionary, there’s new words coming along,” he says. “This is a mechanism for them to update their dictionaries to try to stay current.”

Part of having an up-to-date dictionary also means knowing when to excise words, though, and Sheedy says new Living Language words will expire after six months unless they retain a certain amount of popularity. (“Lochte” may stick around for a while now that the swimmer is getting a reality show.) However, a word added to your phone’s dictionary through Living Language won’t disappear if you’ve used it in Swype, Sheedy says.

Eventually, Sheedy hopes this work can add to the number of languages that Nuance supports. A doctor might use one type of Swype dictionary, while a tech journalist would get another. “I’m just really interested to see how this plays out for us,” he says.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.