Computational Approach To Recognizing Wordplay In Jokes. By Julia Taylor and Lawrence J. Mazlack, Applied Artificial Intelligence Laboratory, ECECS Department, University of Cincinnati . International Humor Conference of the International Society for Humor Studies, Dijon, France, June 2004.
ABSTRACT: "With advancing developments of artificial intelligence, humor researchers have begun to look at approaches for computational humor. Although there appears to be no complete computational model for recognizing verbally expressed humor, it may be possible to recognize jokes based on statistical language recognition techniques. This paper describes an investigation into computational humor recognition. ..."

• Also see Julia Taylor's Masters Thesis: Computational Recognition of Humor In A Focused Domain (May 2004).

Programme information for Passions - Sue Nelson talks to scientists whose hobbies have influenced their scientific work . BBC Radio 4 (June 29, 2004; 09:30). "Kim [Dr Kim Binsted] had always had a love for making people laugh and was part of the improvisational comedy team at school. When her interest in physics and maths took her into artificial intelligence she fell back on her comedy background to help her work on a few problems in computers. Now, having created a programme where computers can generate there own puns, she works on a system that uses comedy to help children learn a new language, whilst still trying to fit a little improv in, in her spare time."

• Dr. Binsted's publications (including some co-authored by Graeme Ritchie) can be found on the Binstead-McCay LLC web site. Her page at the University of Hawaii is here.

ALSO SEE:

• A lot to be learned from computer's bad jokes. By Sam Leith. Telegraph (October 23, 2004). "Computers that can spew out jokes faster and more groanworthy than Jimmy Tarbuck would have dreamed may be a vital tool in teaching children to learn a second language, or in teaching disabled children to speak, an expert in Artificial Intelligence will tell a one-day conference next week. For most of us, being asked 'What do you give a hurt lemon?' and being told, 'lemon aid' sounds like the occasion for deep depression. But the fact that a computer program was able to ask that question and supply that answer has implications for structural linguistics, and for artificial intelligence. And, as Dr Kim Binsted will tell next week's Humour, Art and the Brain festival at Winchester, its applications may go far beyond the automated production of lolly sticks. ... The 'System To Augment Non-speaker's Dialogue Using Puns,' to give [Standup] its full name, helps speech-impaired children incorporate humour into their exchanges. Other versions of the technology can be used in automated 'chatbots' for second-language teaching."
• Cracker joke or two to win a ?500 prize from Asda and be a laugh next year. By David Williamson. The Western Mail / available from ic Wales (December 13, 2003). "One of the reasons such groan-inducing favourites are still attracting interest is that pioneers of artificial intelligence are teaching computers to tell Q&A jokes. So far, computers have learned how puns work and how to match them with nouns and verbs. Tests show that the jokes they have told are almost as funny as those told by humans. And researchers at the University of Edinburgh are hoping to create a 'language playground' where children will be able to experiment with words. Graeme Ritchie said, 'We are aiming it at children with disabilities becausethey are mainly deprived of the thrusting swapping of jokes with their peer group.' In scientific studies their Jape (Joke Analysis and Production Engine) system has amused children."
• Joke-in-a-Box. By Simson Garfinkel. Wired Magazine (Issue 5.03 - Mar 1997). "Creating a computer program that automatically generates jokes is a formidable AI challenge, though, because humor requires large amounts of real-world knowledge. 'Puns use low-level ambiguities to suggest false semantic connections,' says [Kim] Binsted."