A Bona Fide Turing Test
Sharon Temtsin, Diane Proudfoot, Christoph Bartneck · 2022
The constantly rising demand for human-like conversational agents and the accelerated development of natural language processing technology raise expectations for a breakthrough in intelligent machine research and development. However, measuring intelligence is impossible without a proper test. Alan Turing proposed a test for machine intelligence based on imitation and unconstrained conversations between a machine and a human. To the best of our knowledge, no one has ever conducted Turing’s test as Turing prescribed, even though the Turing Test has been a bone of contention for more than seventy years. Conducting a bona fide Turing Test will contribute to machine intelligence evaluation research and has the potential to advance AI researchers in their ultimate quest, developing an intelligent machine.