Evolution of Recursive Transistion Networks for
Natural Language Recognition with Parallel Distributed
Genetic Programming
R. Poli. Evolutionary Computing, volume 1305 of Lecture Notes in Computer Science, page 163--177. Manchester, UK, Springer-Verlag, (11-13 April 1997)
Abstract
This paper describes an application of Parallel
Distributed Genetic Programming (PDGP) to the problem
of inducing recognisers for natural language from
positive and negative examples. PDGP is a new form of
Genetic Programming (GP) which is suitable for the
development of programs with a high degree of
parallelism and an efficient and effective reuse of
partial results. Programs are represented in PDGP as
graphs with nodes representing functions and terminals,
and links representing the flow of control and results.
PDGP allows the exploration of a large space of
possible programs including standard tree-like
programs, logic networks, neural networks, finite state
automata, Recursive Transition Networks (RTNs), etc.
The paper describes the representations, the operators
and the interpreters used in PDGP, and describes how
these can be tailored to evolve RTN-based
recognisers.
see also poli:1996:RTNtr
Proceedings of the Workshop on Artificial Intelligence
and Simulation of Behaviour (AISB) International
Workshop on Evolutionary Computing. Workshop in
Manchester, UK, April 7-8, 1997
Here PDGP was used to evolve recursive transition
networks used to recognise whether natural language
sentences are grammatical. No comparison with GP was
possibile.
%0 Conference Paper
%1 poli:1997:RTN
%A Poli, Riccardo
%B Evolutionary Computing
%C Manchester, UK
%D 1997
%E Corne, David
%E Shapiro, Jonathan L.
%I Springer-Verlag
%K PDGP algorithms, genetic programming,
%P 163--177
%T Evolution of Recursive Transistion Networks for
Natural Language Recognition with Parallel Distributed
Genetic Programming
%U http://citeseer.ist.psu.edu/355686.html
%V 1305
%X This paper describes an application of Parallel
Distributed Genetic Programming (PDGP) to the problem
of inducing recognisers for natural language from
positive and negative examples. PDGP is a new form of
Genetic Programming (GP) which is suitable for the
development of programs with a high degree of
parallelism and an efficient and effective reuse of
partial results. Programs are represented in PDGP as
graphs with nodes representing functions and terminals,
and links representing the flow of control and results.
PDGP allows the exploration of a large space of
possible programs including standard tree-like
programs, logic networks, neural networks, finite state
automata, Recursive Transition Networks (RTNs), etc.
The paper describes the representations, the operators
and the interpreters used in PDGP, and describes how
these can be tailored to evolve RTN-based
recognisers.
%@ 3-540-63476-2
@inproceedings{poli:1997:RTN,
abstract = {This paper describes an application of Parallel
Distributed Genetic Programming (PDGP) to the problem
of inducing recognisers for natural language from
positive and negative examples. PDGP is a new form of
Genetic Programming (GP) which is suitable for the
development of programs with a high degree of
parallelism and an efficient and effective reuse of
partial results. Programs are represented in PDGP as
graphs with nodes representing functions and terminals,
and links representing the flow of control and results.
PDGP allows the exploration of a large space of
possible programs including standard tree-like
programs, logic networks, neural networks, finite state
automata, Recursive Transition Networks (RTNs), etc.
The paper describes the representations, the operators
and the interpreters used in PDGP, and describes how
these can be tailored to evolve RTN-based
recognisers.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Manchester, UK},
author = {Poli, Riccardo},
biburl = {https://www.bibsonomy.org/bibtex/2873c53875a8f57f35c37d3393899b79e/brazovayeye},
booktitle = {Evolutionary Computing},
editor = {Corne, David and Shapiro, Jonathan L.},
interhash = {f0c8bfb3ad862fb0931393301fad6275},
intrahash = {873c53875a8f57f35c37d3393899b79e},
isbn = {3-540-63476-2},
keywords = {PDGP algorithms, genetic programming,},
month = {11-13 April},
notes = {see also \cite{poli:1996:RTNtr}
Proceedings of the Workshop on Artificial Intelligence
and Simulation of Behaviour (AISB) International
Workshop on Evolutionary Computing. Workshop in
Manchester, UK, April 7-8, 1997
Here PDGP was used to evolve recursive transition
networks used to recognise whether natural language
sentences are grammatical. No comparison with GP was
possibile.},
organisation = {AISB},
pages = {163--177},
publisher = {Springer-Verlag},
series = {Lecture Notes in Computer Science},
timestamp = {2008-06-19T17:49:40.000+0200},
title = {Evolution of Recursive Transistion Networks for
Natural Language Recognition with Parallel Distributed
Genetic Programming},
url = {http://citeseer.ist.psu.edu/355686.html},
volume = 1305,
year = 1997
}