An approach to evaluate AI commonsense reasoning systems
Stellan Ohlsson, Robert H. Sloan, György Turán, Daniel Uber, Aaron Urasky · 2012
We propose and give a preliminary test of a new metric for the quality of the commonsense knowledge and rea-soning of large AI databases: Using the same measure-ment as is used for a four-year-old, namely, an IQ test for young children. We report on results obtained us-ing test questions we wrote in the spirit of the questions of the Wechsler Preschool and Primary Scale of Intel-ligence, Third Edition (WPPSI-III) on the ConceptNet system, which were, on the whole, quite strong. 1