This course is run at the The University of Nottingham within the School of Computer Science & IT. The course is run by Graham Kendall (EMAIL : gxk@cs.nott.ac.uk)
The test is conducted with two people and a machine. One person plays the role
of an interrogator and is in a separate room from the machine and the other
person. The interrogator only knows the person and machine as A and B. The interrogator
does not know which is the person and which is the machine.
Using a teletype, the interrogator, can ask A and B any question he/she wishes.
The aim of the interrogator is to determine which is the person and which is
the machine.
The aim of the machine is to fool the interrogator into thinking that it is
a person. If the machine succeeds then we can conclude that machines can think.
The machine is allowed to do whatever it likes in its attempts to fool the interrogator. In 1950 Turing suggested that the machine when presented with a question such as
"How much is 12,324 times 73,981?"
could wait several minutes and then give the wrong answer.
Carrying out the above dialogue is relatively easy. A much more difficult issue
is the amount of knowledge the machine would need to know in order to carry
out a meaningful conversation.
Asking a question such as "Who won last nights top of the table football
match?" would present real problems to a program that was not up to date
on world events and Turing gives the following example dialogue that a machine
would have to be capable of
Interrogator: In the first line of your sonnet which reads "Shall
I compare thee to a summer's day," would not a spring day do as well or
better?
A: It wouldn't scan.
Interrogator: How about "winters day." That would scan all
right.
A: Yes, but nobody wants to be compared to a winter's day.
Interrogator: Would you say that Mr. Pickwick reminded you of Christmas?
A: In a way.
Interrogator: Yet Christmas is a winter's day, and I do not think Mr.
Pickwick would mind the comparison.
A: I don't think you're serious. By a winter's day one means a typical
winter's day, rather than a special one like Christmas.
The Turing Test has yet to be passed and some believe it never will. It is even
argued that passing the Turing Test does not show that a machine is intelligent.
If a program is developed that passes the Turing Test then The Total Turing Test has also been suggested. This test includes video capabilities so that the interrogator can also test the machines perceptual abilities.
But, before we worry about passing The Total-Turing Test we still have the original Turing Test to conquer. And to do this requires that a program is able to process natural language, represent knowledge, reason about the knowledge it has and many other aspects which we regard as demonstrating intelligence.
As well as reading about The Turing Test in the course textbooks, there is a lot of additional material on the web. here are just a few places you might like to visit, but you should also try searching for yourself. Please take the time to read the original paper, which you can see on-line at some of the sites below.
The original Turing Test paper (Turing, A.M. (1950). Computing Machinery and Intelligence. Mind, 59, pp 433-560)can be found at http://www.loebner.net/Prizef/TuringArticle.html
There is lots of other material on The Turing Test at http://www.aaai.org/pathfinder/html/turing.html (including another web site where you can view the original paper)
The Turing Test also has an an annual contest (The Loebner Prize Contest).
Last Updated : 10 Sep 2001