AI Zone Admin Forum Add your forum

NEWS: Chatbots.org survey on 3000 US and UK consumers shows it is time for chatbot integration in customer service!read more..

Judging Partner Identity In A Turing Test
 
 

https://sciencetrends.com/judging-partner-identity-in-a-turing-test/

Two Dutch researchers did a study using Loebner Prize qualifying round transcripts. It turns out that not remembering long-range context correctly (i.e. something said over 5 sentences ago) did not make the answers appear less human. The study also showed that complex sentences were considered less human than straight-forward formulations. Not all too surprising, but there you go.

 

 
  login or register to react