A chatbot named Suzette recently won the Loebner Prize, awarded for a version of the Turing Test, because the system successfully fooled a human judge. Suzette, created by Bruce Wilcox, was programmed to be able to deal with several topics, each with associated rules and responses. "Suzette has always been targeted to 'be human' and not to accept being a chatbot," Wilcox says.
This year's Loebner prize competition required a bot to engage in text-based conversations with judges for 25 minutes. Suzette fooled one judge. Previous winners have fooled more than one judge, but they were only required to maintain a conversation for five minutes. The bot was programmed to converse on several topics, and was programmed to change the subject when it struggled.
"I would say this year has been one of the best so far in terms of the bots' complexity and engineering," says former Loebner prize winner Robby Garner.
From New Scientist
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA
No entries found