Yes, Moor did claim that one would get a better test. He does not represent the bulk of the literature on the subject by any stretch of the imagination. The literature does not clearly show that it is a misreading nor a 'relative waste of time'. The literature has opinions to support both points of view.
1) Yes, the popularised and general understanding of the "turing test" is the "standard" turing test.
2) It does not state that it is indeed a weaker test. It states that there is reason to think it might be. This is in essence something we are interested in understanding.
Turing did call this test "the imitation game" in Computing Machinery and Intelligence:
The new form of the problem can be described' in terms of a game which we call the 'imitation game'.
Thank you for your rather precise and erudite criticism! Whilst I appreciate your seemingly authoritative opinion, and if Alan Turing were here today, I would be happy to be corrected. However, in lieu of Mr. Turing's kind presence, It has been argued very strongly that both interpretations are possible.
From http://plato.stanford.edu/entries/turing-test/#3.1
Now, of course, it is possible to interpret Turing as here intending to say what he seems literally to say, namely, that the new game is one in which the computer must pretend to be a woman, and the other participant in the game is a woman. (See, for example, Genova (1994), and Traiger (2000).) And it is also possible to interpret Turing as intending to say that the new game is one in which the computer must pretend to be a woman, and the other participant in the game is a man who must also pretend to be a woman (cf. Sterrett (2000)). However, as Copeland (2000), Piccinini (2000), and Moor (2001) convincingly argue, the rest of Turing's article, and material in other articles that Turing wrote at around the same time, very strongly support the claim that Turing actually intended the standard interpretation that we gave above, viz. that the computer is to pretend to be a human being, and the other participant in the game is a human being of unspecified gender. Moreover, as Moor (2001) argues against the claims of Sterrett (2000), there is no reason to think that one would get a better test if the computer must pretend to be a woman and the other participant in the game is a man pretending to be a woman (and, indeed, there is some reason to think that one would get a worse test).
Therefore, the language "imitation game" does attempt to set itself apart from the common usage of "turing test", and it also adopts a philosophical opinion on the interpretation.
We were initially very interested in conducting a full matrix of variable combinations- however, as this was an initial test, we decided to use only a few variables, and have more control over the experiment.
I hope to comment upon your questions in our final paper.
We just performed the experiment this past Saturday, and are conducting the statistical analysis now.
I agree with you, however- the results will be the most interesting aspect of this experiment.
We will complete our analysis soon and we will be able to publish the results.
So, no- you aren't missing anything- other than we performed the experiment for the first time.
The Loebner Prize is a test of the "Standardised Turing Test", not the imitation game written about in Turing's original paper. That was the entire point of doing the experiment.
You can read more about the difference between the Original Imitation Game and the Standardised "Turing Test" here:
http://www.alicebot.org/articles/wallace/lying.htm l
I generally agree that the popularlised "Turing Test" is generally uninteresting and uninformative. This was the main reason for our Imitation Game experiment. We noticed that no one had ever performed an experiment of this measure- and we were curious what kind of results it actually produced. It is difficult for me to write off the value of a test that has never actually been performed.
We just performed the experiment this past Saturday, and we are currently performing a statistical analysis on it. We hope to submit the results in the form of a paper in the near future.
The reason we required our participants to be over 18 is because of informed consent. If our participants were under 18- they would need a signed parental consent form to participate in our experiment.
I am the lead researcher for this experiment-
The main reason why I feel that this test was interesting is because we performed Turing's original imitation game as stated in his original paper. While most social scientists believe they "know" what the "Turing Test" is- it turns out- very few of them have actually read it. The actual imitation game is a bit of a bait and switch- you aren't directly assessing the "humanness" of the subject- you are confused into just trying to assess an aspect of it. Turing's original question was simply how often will judges correctly guess the real female over the deciever when the deciever is a male versus a machine?
That was what we were attempting to assess.
Slashdot Mirror
Yes, Moor did claim that one would get a better test. He does not represent the bulk of the literature on the subject by any stretch of the imagination. The literature does not clearly show that it is a misreading nor a 'relative waste of time'. The literature has opinions to support both points of view.
1) Yes, the popularised and general understanding of the "turing test" is the "standard" turing test.
2) It does not state that it is indeed a weaker test. It states that there is reason to think it might be. This is in essence something we are interested in understanding.
Turing did call this test "the imitation game" in Computing Machinery and Intelligence: The new form of the problem can be described' in terms of a game which we call the 'imitation game'.
We were initially very interested in conducting a full matrix of variable combinations- however, as this was an initial test, we decided to use only a few variables, and have more control over the experiment. I hope to comment upon your questions in our final paper.
We just performed the experiment this past Saturday, and are conducting the statistical analysis now. I agree with you, however- the results will be the most interesting aspect of this experiment. We will complete our analysis soon and we will be able to publish the results. So, no- you aren't missing anything- other than we performed the experiment for the first time.
The Loebner Prize is a test of the "Standardised Turing Test", not the imitation game written about in Turing's original paper. That was the entire point of doing the experiment. You can read more about the difference between the Original Imitation Game and the Standardised "Turing Test" here: http://www.alicebot.org/articles/wallace/lying.htm l
I generally agree that the popularlised "Turing Test" is generally uninteresting and uninformative. This was the main reason for our Imitation Game experiment. We noticed that no one had ever performed an experiment of this measure- and we were curious what kind of results it actually produced. It is difficult for me to write off the value of a test that has never actually been performed.
We just performed the experiment this past Saturday, and we are currently performing a statistical analysis on it. We hope to submit the results in the form of a paper in the near future.
The reason we required our participants to be over 18 is because of informed consent. If our participants were under 18- they would need a signed parental consent form to participate in our experiment.
I am the lead researcher for this experiment- The main reason why I feel that this test was interesting is because we performed Turing's original imitation game as stated in his original paper. While most social scientists believe they "know" what the "Turing Test" is- it turns out- very few of them have actually read it. The actual imitation game is a bit of a bait and switch- you aren't directly assessing the "humanness" of the subject- you are confused into just trying to assess an aspect of it. Turing's original question was simply how often will judges correctly guess the real female over the deciever when the deciever is a male versus a machine? That was what we were attempting to assess.