Helping AI get the joke

Can AI succeed where the American people have failed, and understand British sarcasm?

I’m kidding, I’m kidding.

But this is an interesting project over at Purdue University, via Phys.org:

Julia Rayz is conducting artificial intelligence research involving humor, among other areas, to determine what is necessary through computational algorithms to create computer-human interaction that rivals a common conversation between people.

“I don’t try to teach computers to tell funny jokes; I want to use artificial intelligence to get computers to a point where they understand why we think something is funny or not,” said Rayz, an associate professor in Purdue University’s Department of Computer and Information Technology.

How do you do that? With great difficulty. This is another instance of it being incredibly hard to teach AI something that humans find instinctively easy.

Rayz’ research involves trying to provide artificial intelligence with understandings of what makes a joke a joke, looking at facets such as delivery, context and emotion. To reach comprehension, the computer also needs to have a lot of background knowledge about the situation that the joke describes.

Finally, the artificial intelligence must have a perfect understanding of every single meaning that is used in that joke and be able combine it together and interpret the meaning behind what is being said.

Why is all this important in the development of AI? Well, detecting sarcasm, and understanding when the human in charge is making a jokey request, is vital if voice assistants are to feel more genuine than they do now. The article mentions that if you ask Alexa to tell you a joke today it’s a wooden, emotionless delivery.

That needs to improve if AI is to move forward, says Rayz:

“Artificial intelligence should be able to handle more natural conversation and understand when you are joking and when you are serious,” she said. “If you are giving a command in a sarcastic manner, the computer needs to know it does not need to follow that command.”

On a related note, I greatly enjoyed Ashlee Vance exploring the possibility that robots might one day be funny in this piece aired last year:

Let’s be honest, though – humans doing improv are rarely funny. What chance did the robot have?