One Step Closer to True AI, New Robot Gets Jokes

In Ars technica, (for Maya Nair):

Knock knock
Who’s there?
Orange.
Orange who?
Orange you glad I didn’t say banana?

This is the kind of humor we’re used to hearing from kids, colleagues who think they are funnier than they really are, and the likes of Steve Wozniak. Well, Woz may have a newly-interested audience for his hilarious joke-telling appearances, because researchers at the University of Cincinnati have developed a robot that is capable of recognizing simple humor made up of wordplay and bad puns.

“The ability to appreciate humor is an enormous increment in subtlety,” said researcher Tom Mantei from the University of Cincinnati’s College of Engineering in a statement. “You need to know a lot to ‘get’ humor—a computer does not find it easy.”

That’s what UC doctoral student Julia Taylor and professor Larry Mazlack have discovered in their project on data mining. They reported on their progress with the project at the American Association for Artificial Intelligence conference in Vancouver this week, and while they feel they have made great progress so far, they also feel that they have a long way to go.

“The ‘robot’ is just a software program that still needs a lot of work,” says Taylor. “The idea is to be able to recognize jokes that are based on phonological similarity of words.”

The software recognizes humor by processing the words used in the joke and comparing it with a vocabulary database, which must be created by a world-wise human being.

[H/t: Anandaroop Roy.]