This repository has been archived on 2023-08-20. You can view files and clone it, but cannot push or open issues or pull requests.
yap-6.3/packages/cplint/rib
Fabrizio Riguzzi be449b3aef updated cplint 2011-10-22 16:33:04 +02:00
..
Artistic updated cplint 2011-10-22 16:33:04 +02:00
README updated cplint 2011-10-22 16:33:04 +02:00
hmml2.cpl updated cplint 2011-10-22 16:33:04 +02:00
hmml2.kb updated cplint 2011-10-22 16:33:04 +02:00
hmml2.l updated cplint 2011-10-22 16:33:04 +02:00
hmml2.rules updated cplint 2011-10-22 16:33:04 +02:00
inference_ib.pl updated cplint 2011-10-22 16:33:04 +02:00
rib.pl updated cplint 2011-10-22 16:33:04 +02:00
sp1.cpl updated cplint 2011-10-22 16:33:04 +02:00
sp1.kb updated cplint 2011-10-22 16:33:04 +02:00
sp1.l updated cplint 2011-10-22 16:33:04 +02:00
sp1.rules updated cplint 2011-10-22 16:33:04 +02:00
sp1npn.cpl updated cplint 2011-10-22 16:33:04 +02:00
sp1npn.kb updated cplint 2011-10-22 16:33:04 +02:00
sp1npn.l updated cplint 2011-10-22 16:33:04 +02:00
sp1npn.rules updated cplint 2011-10-22 16:33:04 +02:00

README

This folder cotains RIB, a parameter learning algorithm based on the information bottleneck

To execute rib, load ib.pl with

:- use_module(library('cplint/rib')).

and run

:- ib_par(filestem).

in a directory containing filestem.kb, filestem.bg and filestem.l.
You will find the output in filestem.rules.

The folder contains the following examples 
sp1 and sp1npn (first fold of IMDB for target predicate sameperson)
hmml2: hidden markov model

In the .l file you should specify input and output (taget predicates) in the form

input(pred/arity).

output(pred/arity).

See also http://sites.unife.it/rib/