The Loebner Prize
In 1990 philanthropist Hugh Loebner offered a $100,000 prize to the first software to pass the Turing test. Computers face off with humans annually in special version of the Test. And, if no computer passes, an award is made to the best peformer.
The Loebner version of the Turing Test

This version of the Turing test adds several measures to make it practical:

  • Test questions are restricted to pre-determined topics (see Restricted Turing Tests, Box 14).
  • Referees watch to make sure judges stick to the topics and ask fair questions without trickery or guile.
  • Prizes are awarded using a novel scoring method. Judges ranjk the contestants relative to one another rather than just passing or failing them.
  • The highest scoring computer in each contest is the yearly winner, and if a computer's score is equal to greater than the average score of a human contestant, then it passes this version of the Turing test and wins the $100,000 prize.
The Loebner Prize website describes the background to the prize as follows:

"The Loebner Prize for artificial intelligence ( AI ) is the first formal instantiation of a Turing Test. The test is named after Alan Turing the brilliant British mathematician. Among his many accomplishments was basic research in computing science. In 1950, in the article Computing Machinery and Intelligence which appeared in the philosophy journal Mind, Alan Turing asked the question "Can a Machine Think?" He answered in the affirmative, but a central question was: "If a computer could think, how could we tell?" Turing's suggestion was, that if the responses from the computer were indistinguishable from that of a human,the computer could be said to be thinking. This field is generally known as natural language processing.

In 1990 Hugh Loebner agreed with The Cambridge Center for Behavioral Studies to underwrite a contest designed to implement the Turing Test. Dr. Loebner pledged a Grand Prize of $100,000 and a Gold Medal (pictured above) for the first computer whose responses were indistinguishable from a human's. Such a computer can be said "to think." Each year an annual prize of $2,000 and a bronze medal is awarded to the most human-like computer. The winner of the annual contest is the best entry relative to other entries that year, irrespective of how good it is in an absolute sense."


Judith Gunther attended the Loebner test in 1994 for Popular Science in June 1994, and noted:

"Using this test to define artificial intelligence, the Loebner Prize Competition places judges—all journalists like myself—at a series of computer terminals that are linked to unidentified conversationalists. Some are humans sitting at terminals in a room down the hall, some are software programs running off their creator's computers hundreds of miles away. As the judges type in and receive messages, they must decide the nature—living or silicon--of their unseen correspondents. The judges rotate twice among the different terminals, spending a total of 15 minutes with each hidden entity. The conversations are limited to predetermined topics (baseball, for example) which are posted next to each terminal" (Gunther, 1994, p. 90).

"The contest took place in a small, square room lined with eight identical computer terminals. To make sure that no one wandered too far off the designated topics, stern-looking referees kept peering over the judges shoulders at the glowing screens" (Gunther, 1994, p. 91).

Gunther, Judith A., (1994), "A Encounter with AI," Popular Science, June 1994, pp. 90-93

Λεπτομέρειες πλοηγού
(Βοήθεια)
-
Artificial Intelligence »Artificial Intelligence
Can the Turing Test determine this? [2]  »Can the Turing Test determine this? [2] 
The Loebner Prize
Loebner prize is a useful stimulus to AI research »Loebner prize is a useful stimulus to AI research
+Σχόλια (0)
+Αναφορές (0)
+About