Richard> Eric Baum wrote: >>>>> I don't think the proofs depend on any special assumptions about >>>> the > nature of learning. >>>> >>>> I beg to differ. IIRC the sense of "learning" they require is >>>> induction over example sentences. They exclude the use of real >>>> world knowledge, in spite of the fact that such knowledge (or at >>>> least <primitives involved in the development of real world knowledge> ) are posited to play a significant role in the learning >>>> of grammar in humans. As such, these proofs say nothing >>>> whatsoever about the learning of NL grammars. >>>> >> I fully agree the proofs don't take into account such stuff. And I >> believe such stuff is critical. Thus I've never claimed language >> learning was proved hard, I've just suggested evolution could have >> encrypted it. >> >> The point I began with was, if there are lots of different locally >> optimal codings for thought, it may be hard to figure out which one >> is programamed into the mind, and thus language learning could be a >> hard additional problem to producing an AGI. The AGI has to >> understand what the word "foobar" means, and thus it has to have >> (or build) a code module meaning ``foobar" that it can invoke with >> this word. If it has a different set of modules, it might be sunk >> in communication. >> >> My sense about grammars for natural language, is that there are >> lots of different equally valid grammars that could be used to >> communicate. For example, there are the grammars of English and of >> Swahili. One isn't better than the other. And there is a wide >> variety of other kinds of grammars that might be just as good, that >> aren't even used in natural language, because evolution chose one >> convention at random. Figuring out what that convention is, is >> hard, at least Linguists have tried hard to do it and failed. And >> this grammar stuff is pretty much on top of, the meanings of the >> words. It serves to disambiguate, for example for error correction >> in understanding. But you could communicate pretty well in pidgin, >> without it, so long as you understand the meanings of the words. >> >> The grammar learning results (as well as the experience of >> linguists, who've tried very hard to build a model for natural >> grammar) I think, are indicative that this problem is hard, and it >> seems that this problem is superimposed above the real world >> knowledge aspect.
Richard> Eric, Richard> Thankyou, I think you have focussed down on the exact nature Richard> of the claim. Richard> My reply could start from a couple of different places in Richard> your above text (all equivalent), but the one that brings out Richard> the point best is this: >> And there is a wide variety of other kinds of grammars that might >> be just as good, that aren't even used in natural language, because >> evolution chose one convention at random. Richard> Richard> ^^^^^^ Richard> This is precisely where I think the flase assumption is Richard> buried. When I say that grammar learning can be dependent on Richard> real world knowledge, I mean specifically that there are Richard> certain conceptual primitives involved in the basic design of Richard> a concept-learning system. We all share these primitives, Richard> and [my claim is that] our language learning mechanisms start Richard> from those things. Because both I and a native Swahili Richard> speaker use languages whose grammars are founded on common Richard> conceptual primitives, our grammars are more alike than we Richard> imagine. Richard> Not only that, but if myself and the Swahili speaker suddenly Richard> met and tried to discover each other's languages, we would be Richard> able to do so, eventually, because our conceptual primitives Richard> are the same and our learning mechanisms are so similar. Richard> Finally, I would argue that most cognitive systems, if they Richard> are to be successful in negotiating this same 3-D universe, Richard> would do best to have much the same conceptual primitives Richard> that we do. This is much harder to argue, but it could be Richard> done. Richard> As a result of this, evolution would not by any means have Richard> been making random choices of languages to implement. It Richard> remains to be seen just how constrained the choices are, but Richard> there is at least a prima facie case to be made (the one I Richard> just sketched) that evolution was extremely constrained in Richard> her choices. Richard> In the face of these ideas, your argument that evolution Richard> essentially made a random choice from a quasi-infinite space Richard> of possibilities needs a great deal more to back it up. The Richard> grammar-from-conceptual-primitives idea is so plausible that Richard> the burden is on you to give a powerful reason for rejecting Richard> it. Richard> Correct me if I am wrong, but I see no argument from you on Richard> this specific point (maybe there is one in your book .... but Richard> in that case, why say without qualification, as if it was Richard> obvious, that evolution made a random selection?). Richard> Unless you can destroy the grammar-from-conceptual-primitives Richard> idea, surely these arguments about hardness of learning have Richard> to be rejected? The argument, in very brief, is the following. Evolution found a very compact program that does the right thing. (This is my hypothesis, not claimed proved but lots of reasons to believe it given in WIT?.) Finding such programs is NP-hard. The same arguments indicate, you don't need to find the global optimum, shortest best program, for it to work, and there's no reason to believe evolution did. You just need to find a sufficiently good one (which is still typically NP-hard.) Lots of experience with analogous such problems (and various theoretical arguments) shows that there usually are lots (in fact, exponentially many) of locally optimal solutions that don't look like each other in detail. For example, consider domain structure in crystals. That's a case where there is a single global optimum-- but you don't actually find it. If you do it twice, you will find different domain structures. Cases such as spin glasses, are likely to be even worse. Evolution picked one conceptual structure, but there are likely to be many that are just as good. Communication, however, may well depend on having a very similar conceptual structure. Also, in addition to getting the conceptual structure right, I expect that grammar involves lots of other choices that are essentially just notational choices, purely arbitrary, on top of the actual computational modules, only concerned with parsing communication streams between different individuals. Yes English speakers and Swahili's have all these other choices in common, because they are essentially evolved into the genome. But that does not mean that these choices are in any way determined, even assuming you get the conceptual structure the same. This stuff could be purely notational. Its this stuff that the hardness of grammar learning results pertains most too, this is what Chomsky/Pinker mean when they talk about inborn language instinct, all this literature does ignore semantics, but that's because (at least in large part) this literature believes there's a notational ambiguity. Since clearly there could be such a notational ambiguity, to believe there isn't, you have to posit a reason why it wouldn't arise. Evolution just short circuits this by choosing a notation, but figuring out what notation can be a hard problem, since determining a grammar from examples is hard. Richard> Richard Loosemore Richard> ----- This list is sponsored by AGIRI: Richard> http://www.agiri.org/email To unsubscribe or change your Richard> options, please go to: Richard> http://v2.listbox.com/member/?list_id=303 ----- 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/?list_id=303
