[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [computer-go] Automatic acquisition of syntactic structures
One of the main places to find this kind
of research is in the grammatical inference
(aka grammar induction) community:
The problem is indeed very difficult, but
some of the early directions have become
very practical methods that are routinely
applied - such as hidden Markov models
(roughly equivalent to stochastic regular
grammars) for example.
In many cases, to make the inference
problem tractable, some restrictive assumptions
are made on the form of the model, and then
just the statistics rather than the structure
are estimated from the data - using
fast converging methods such as expectation
I think there's a lot of scope for applying these
methods to games such as Go.
From: computer-go-bounces@xxxxxxxxxxxxxxxxx [mailto:computer-go-bounces@xxxxxxxxxxxxxxxxx] On Behalf Of Robin Kramer
Sent: 28 September 2005 15:11
Subject: Re: [computer-go] Automatic acquisition of syntactic structures
Well, I am interested in this topic as well. I have attended a couple of talks on the area, and I think the research has branched into Inductive Logic Programming(ILP), and chart parsing.
The research in the seventies was great though, maybe they discovered that the problem was really very difficult.
On 9/28/05, Toni Cebrian <cebrian@xxxxxxxxxxxxxxxxx> wrote:
> I don't know if you are proficient in this area but I'd like some
> advice on finding references, books, tutorials about Syntactic Pattern
> Recognition. It's being difficult to me to find material to read and
> almost all books date from the 70's and are hard to find. What
> happened with this area of AI research?
> Bob Myers escribió:
> > I wonder if any computer go researchers have seen this paper
> > http://www.tau.ac.il/~zsolan/papers/soletalb2002.pdf
> > entitled "Automatic acquisition and efficient representation of
> > syntactic structures", and claiming to be an algorithm for learning
> > "sequences", not only language-based but also "sheet music or
> > protein sequences".
> > Thoughts?
> > --
> > Bob Myers
> > _______________________________________________
> > computer-go mailing list
> > computer-go@xxxxxxxxxxxxxxxxx
> > http://www.computer-go.org/mailman/listinfo/computer-go/
> computer-go mailing list
computer-go mailing list