Jabberwacky and Jabberwock

We're reading Sherry Turkle's Life on the Screen in Internet Writing & Society, and tomorrow we're discussing artificial intelligence. While googling around trying to see if there was a working version of Depression 2.0 out there, I ran across Jabberwacky, a Web chatterbot that took 3rd place in the 2003 Loebner Prize. The bot is different from earlier systems, such as the classic Eliza, in that it learns from the aggregate knowledege of its users: “It stores everything everyone has ever said, and finds the most appropriate thing to say using contextual pattern matching techniques. In speaking to you it uses only learnt material. With no hard-coded rules, it relies entirely on the principles of feedback. This is very different to the majority of chatbots, which are rule-bound and finite.” The bot provides a compelling experience. While it wouldn't pass a Turing test, it returns some very interesting responses, and can respond in many different languages (Jill had a little chat with it in Norwegian, and it was capable of sliding in between French and English just as well as I could [which isn't saying much]). The winner of the 2003 Loebner Prize, Jabberwock actually comes a lot closer to passing a Turing test, even though its system is more like the standard “Eliza-style” AI.