Interesting. Since I am interested in parsing, I read Collin's paper. It's a solid piece of work (though with the stated error percentages, I don't believe that it really proves anything worthwhile at all) -- but your over-interpretations of it are ridiculous.
You claim that "It is actually showing that you can do something roughly equivalent to growing neural gas (GNG) in a space with something approaching 500,000 dimensions, but you can do it without normally having to deal with more than a few of those dimensions at one time." Collins makes no claims that even remotely resembles this. He *is* taking a deconstructionist approach (which Richard and many others would argue vehemently with) -- but that is virtually the entirety of the overlap between his paper and your claims. Where do you get all this crap about 500,000 dimensions, for example? You also make statements that are explicitly contradicted in the paper. For example, you say "But there really seem to be no reason why there should be any limit to the dimensionality of the space in which the Collin's algorithm works, because it does not use an explicit vector representation" while his paper quite clearly states "Each tree is represented by an n dimensional vector where the i'th component counts the number of occurences of the i'th tree fragment." (A mistake I believe you made because you didn't understand the prevceding sentence -- or, more critically, *any* of the math). Are all your claims on this list this far from reality if one pursues them? ----- Original Message ----- From: "Ed Porter" <[EMAIL PROTECTED]> To: <agi@v2.listbox.com> Sent: Tuesday, December 04, 2007 10:52 PM Subject: RE: Hacker intelligence level [WAS Re: [agi] Funding AGI research] The particular NL parser paper in question, Collins's "Convolution Kernels for Natural Language" (http://l2r.cs.uiuc.edu/~danr/Teaching/CS598-05/Papers/Collins-kernels.pdf) is actually saying something quite important that extends way beyond parsers and is highly applicable to AGI in general. It is actually showing that you can do something roughly equivalent to growing neural gas (GNG) in a space with something approaching 500,000 dimensions, but you can do it without normally having to deal with more than a few of those dimensions at one time. GNG is an algorithm I learned about from reading Peter Voss that allows one to learn how to efficiently represent a distribution in a relatively high dimensional space in a totally unsupervised manner. But there really seem to be no reason why there should be any limit to the dimensionality of the space in which the Collin's algorithm works, because it does not use an explicit vector representation, nor, if I recollect correctly, a Euclidian distance metric, but rather a similarity metric which is generally much more appropriate for matching in very high dimensional spaces. But what he is growing are not just points representing where data has occurred in a high dimensional space, but sets of points that define hyperplanes for defining the boundaries between classes. My recollection is that this system learns automatically from both labeled data (instances of correct parse trees) and randomly generated deviations from those instances. His particular algorithm matches tree structures, but with modification it would seem to be extendable to matching arbitrary nets. Other versions of it could be made to operate, like GNG, in an unsupervised manner. If you stop and think about what this is saying and generalize from it, it provides an important possible component in an AGI tool kit. What it shows is not limited to parsing, but it would seem possibly applicable to virtually any hierarchical or networked representation, including nets of semantic web RDF triples, and semantic nets, and predicate logic expressions. At first glance it appears it would even be applicable to kinkier net matching algorithms, such as an Augmented transition network (ATN) matching. So if one reads this paper with a mind to not only what it specifically shows, but to what how what it shows could be expanded, this paper says something very important. That is, that one can represent, learn, and classify things in very high dimensional spaces -- such as 10^1000000000000 dimensional spaces -- and do it efficiently provided the part of the space being represented is sufficiently sparsely connected. I had already assumed this, before reading this paper, but the paper was valuable to me because it provided a mathematically rigorous support for my prior models, and helped me better understand the mathematical foundations of my own prior intuitive thinking. It means that systems like Novemente can deal in very high dimensional spaces relatively efficiently. It does not mean that all processes that can be performed in such spaces will be computationally cheap (for example, combinatorial searches), but it means that many of them, such as GNG like recording of experience, and simple indexed based matching can scale relatively well in a sparsely connected world. That is important, for those with the vision to understand. Ed Porter -----Original Message----- From: Benjamin Goertzel [mailto:[EMAIL PROTECTED] Sent: Tuesday, December 04, 2007 8:59 PM To: agi@v2.listbox.com Subject: Re: Hacker intelligence level [WAS Re: [agi] Funding AGI research] > Thus: building a NL parser, no matter how good it is, is of no use > whatsoever unless it can be shown to emerge from (or at least fit with) > a learning mechanism that allows the system itself to generate its own > understanding (or, at least, acquisition) of grammar IN THE CONTEXT OF A > MECHANISM THAT ALSO ACCOMPLISHES REAL UNDERSTANDING. When that larger > issue is dealt with, a NL parser will arise naturally, and any previous > work on non-developmental, hand-built parsers will be completely > discarded. You were trumpeting the importance of work that I know will > be thrown away later, and in the mean time will be of no help in > resolving the important issues. Richard, you discount the possibility that said NL parser will play a key role in the adaptive emergence of a system that can generate its own linguistic understanding. I.e., you discount the possibility that, with the right learning mechanism and instructional environment, hand-coded rules may serve as part of the initial seed for a learning process that will eventually generate knowledge obsoleting these initial hand-coded rules. It's fine that you discount this possibility -- I just want to point out that in doing so, you are making a bold and unsupported theoretical hypothesis, rather than stating an obvious or demonstrated fact. Vaguely similarly, the "grammar" of child language is largely thrown away in adulthood, yet it was useful as scaffolding in leading to the emergence of adult language. -- Ben G ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?& ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?& ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=72260752-a8b2ee