Everyone's a Critic: Memory Models and Uses for an Artificial Turing Judge
W. Joseph MacInnes, Blair C. Armstrong, Dwayne Pare, George S. Cree, Steve Joordens
W. Joseph MacInnes
Available Online June 2009.
- https://doi.org/10.2991/agi.2009.34How to use a DOI?
- The Turing test was originally conceived by Alan Turing  to determine if a machine had achieved human-level intelligence. Although no longer taken as a comprehensive measure of human intelligence, passing the Turing test remains an interesting challenge as evidenced by the still unclaimed Loebner prize, a high profile prize for the first AI to pass a Turing style test. In this paper, we sketch the development of an artificial "Turing judge" capable of critically evaluating the likelihood that a stream of discourse was generated by a human or a computer. The knowledge our judge uses to make the assessment comes from a model of human lexical semantic memory known as latent semantic analysis. We provide empirical evidence that our implemented judge is capable of distinguishing between human and computer generated language from the Loebner Turing test competition with a degree of success similar to human judges. Keywords Semantic Memory, General Knowledge, Decision Making, Machine learning, Language, Turing test.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - W. Joseph MacInnes AU - Blair C. Armstrong AU - Dwayne Pare AU - George S. Cree AU - Steve Joordens PY - 2009/06 DA - 2009/06 TI - Everyone's a Critic: Memory Models and Uses for an Artificial Turing Judge BT - Proceedings of the 2nd Conference on Artificiel General Intelligence (2009) PB - Atlantis Press SP - 158 EP - 163 SN - 1951-6851 UR - https://doi.org/10.2991/agi.2009.34 DO - https://doi.org/10.2991/agi.2009.34 ID - MacInnes2009/06 ER -