Microsoft researchers aim to teach artificial intelligence (AI) software how humor works by training it on an archive of New Yorker cartoons and entries into the magazine's cartoon caption contest. Researcher Dafna Shahaf fed the cartoons and contest entries to the software and taught it to select the funniest choices among captions that make similar jokes, relying partly on crowdsourced input from contract workers via Amazon.com's Mechanical Turk. Ranking jokes was the next step, requiring the researchers to manually describe what was happening in each cartoon, and to categorize its context and anomalies.
The AI system is capable of weeding out poor caption-contest submissions and narrowing the list to the funnier ones. New Yorker cartoon editor Bob Mankoff thinks AI could become a useful aid for humorists, once the Microsoft system can select captions with greater accuracy. The Microsoft researchers also want to train computers to invent their own situational jokes.
In a wider context, understanding what people find funny and how they come up with jokes is an important area in the field of brain dynamics, which also is essential to AI research.
From Bloomberg
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found