MIT Technology Review Subscribe

Every Spreadsheet Has a Narrative to Tell—Just Add Some AI

To make sense of data, we are teaching computers to speak our language.

Every day, we export 2.5 quintillion bytes of data out of our ubiquitous machines. This data comes in forms from million-row spreadsheets to photos of local coffee shops. It is filled with information, but most of it is not naturally in a form humans can understand. Kris Hammond, chief scientist and cofounder of Narrative Science, is transforming this data into language.

“Language by itself is miraculous and uniquely human,” Hammond told the audience at EmTech MIT on Tuesday. “You can teach a dog things; crows use tools; beavers use dams. There is no other creature that uses language the way we use language. Although machines use words, they struggle with language.”

Advertisement

Humans innately connect complex ideas in our heads, Hammond said, because of our experience with language. Enabling machines to communicate using the same language as we do becomes ever more critical as machines become a larger part of our lives.

This story is only available to subscribers.

Don’t settle for half the story.
Get paywall-free access to technology news for the here and now.

Subscribe now Already a subscriber? Sign in
You’ve read all your free stories.

MIT Technology Review provides an intelligent and independent filter for the flood of information about technology.

Subscribe now Already a subscriber? Sign in

Narrative Science is using AI to teach machines this human skill. Its software, Quill, can take data like the box score of a baseball game, summarize the content, and extract a “narrative” from it (see “Who Will Own the Robots?”). Now, instead of staring at a bewildering compilation of numbers, you can view an easy-to-read paragraph telling you what you need to know.

“We have struggled with data for a long time. We shouldn’t be struggling with it; the machine should be presenting it to us,” Hammond said.

The city of Chicago has taken this approach to synthesize data about miles of its shorelines. It records data on numerous beaches and creates cumbersome spreadsheets. Using Quill, the city boils the information in the spreadsheets down to digestible statements indicating the best and worst beaches in the city.

Turning data into language can also benefit businesses and their customers.

“Most people who have jobs don’t also want to look at data and find out what’s going on,” Hammond said. “You don’t want to hand data to people who run the deli. You take that exact same data and turn it into reports to give them advice about what they might be able to do next.”

This is your last free story.
Sign in Subscribe now

Your daily newsletter about what’s up in emerging technology from MIT Technology Review.

Please, enter a valid email.
Privacy Policy
Submitting...
There was an error submitting the request.
Thanks for signing up!

Our most popular stories

Advertisement