[Corpora-List] No poverty of the stimulus

[P Resnik]

Rich, thank you for posting this pointer!  I have not yet had a chance to
read the paper, but on a quick scan, I notice that they do not reference

Shyam Kapur, "Computational Learning of Languages",  Cornell dissertation,
1991.  http://portal.acm.org/citation.cfm?id=866568 .  Postscript and PDF
available at http://ecommons.library.cornell.edu/handle/1813/7074.

I suspect that anyone interested in the Chater and Vitanyi paper will also
find this of interest, particularly the results of Chapter 5, where
Kapurwrites, "... in accordance to a suggestion due to Gold (1967),
maybe we can
learn more families if we insist on convergence on most (instead of all)
texts [i.e. sequences of sentences presented as positive examples to the
learner -PSR]".  His work shows that with this convergence criterion, it is
possible to obtain "a uniform learning algorithm that works for *every *family
of languages" [my emphasis], subject to stochastic assumptions about the
input that, if I understood/recall correctly, avoid problems with the sorts
of pathological texts the Gold's proof relied on.

Happy holidays,

  Philip
`


On Dec 27, 2007 12:41 PM, Rich Cooper <Rich at englishlogickernel.com> wrote:

> Not everyone seems to believe that the "poverty of the stimulus" is a
> valid
> argument.
>
> Here is a mathematically supported paper that provides a deep treatment of
> learning language
> "Ideal Learning of Natural Language: Positive Results from Learning about
> Positive Evidence"
> by Nick Chater at Univ Coll London:
> http://eprints.pascal-network.org/archive/00002798/01/jmp06.pdf
>
> His claim is that an ideal learner, using Kolmogorov complexity methods,
> can
> provide both the positive and the negative learning needed for an ideal
> learner, even though only given positive evidence.  The absence of
> evidence
> for certain constructions is treated as evidence that those constructions
> are ungrammatical.
>
> Comments appreciated.
>
> Sincerely,
> Rich Cooper
> http://www.EnglishLogicKernel.com
>
>
>
>
>
> _______________________________________________
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20071227/7a179d3d/attachment.htm>
-------------- next part --------------
_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora