Evolution of Logic Programs: Part-of-Speech Tagging
P. Reiser, и P. Riddle. Proceedings of the Congress on Evolutionary
Computation, 2, стр. 1338--1346. Mayflower Hotel, Washington D.C., USA, IEEE Press, (6-9 July 1999)
Аннотация
An algorithm is presented for learning concept
classification rules. It is a hybrid between
evolutionary computing and inductive logic programming
(ILP). Given input of positive and negative examples,
the algorithm constructs a logic program to classify
these examples. The algorithm has several attractive
features, including the ability to use explicit
background (user-supplied) knowledge and to produce
comprehensible output. We present results of using the
algorithm to a natural language processing problem,
part-of-speech tagging. The results indicate that using
an evolutionary algorithm to direct a population of ILP
learners can increase accuracy. This result is further
improved when crossover is used to exchange rules at
intermediate stages in learning. The improvement over
Progol, a greedy ILP algorithm, is statistically
significant (P<0.005)
%0 Conference Paper
%1 reiser:1999:ELPPT
%A Reiser, Philip G. K.
%A Riddle, Patricia J.
%B Proceedings of the Congress on Evolutionary
Computation
%C Mayflower Hotel, Washington D.C., USA
%D 1999
%E Angeline, Peter J.
%E Michalewicz, Zbyszek
%E Schoenauer, Marc
%E Yao, Xin
%E Zalzala, Ali
%I IEEE Press
%K ILP algorithms, data evolutionary genetic inductive language logic mining, natural processing, programming,
%P 1338--1346
%T Evolution of Logic Programs: Part-of-Speech Tagging
%U http://www.stancomb.co.uk/~prr/Papers/cec99.ps
%V 2
%X An algorithm is presented for learning concept
classification rules. It is a hybrid between
evolutionary computing and inductive logic programming
(ILP). Given input of positive and negative examples,
the algorithm constructs a logic program to classify
these examples. The algorithm has several attractive
features, including the ability to use explicit
background (user-supplied) knowledge and to produce
comprehensible output. We present results of using the
algorithm to a natural language processing problem,
part-of-speech tagging. The results indicate that using
an evolutionary algorithm to direct a population of ILP
learners can increase accuracy. This result is further
improved when crossover is used to exchange rules at
intermediate stages in learning. The improvement over
Progol, a greedy ILP algorithm, is statistically
significant (P<0.005)
%@ 0-7803-5537-7 (Microfiche)
@inproceedings{reiser:1999:ELPPT,
abstract = {An algorithm is presented for learning concept
classification rules. It is a hybrid between
evolutionary computing and inductive logic programming
(ILP). Given input of positive and negative examples,
the algorithm constructs a logic program to classify
these examples. The algorithm has several attractive
features, including the ability to use explicit
background (user-supplied) knowledge and to produce
comprehensible output. We present results of using the
algorithm to a natural language processing problem,
part-of-speech tagging. The results indicate that using
an evolutionary algorithm to direct a population of ILP
learners can increase accuracy. This result is further
improved when crossover is used to exchange rules at
intermediate stages in learning. The improvement over
Progol, a greedy ILP algorithm, is statistically
significant (P<0.005)},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Mayflower Hotel, Washington D.C., USA},
author = {Reiser, Philip G. K. and Riddle, Patricia J.},
biburl = {https://www.bibsonomy.org/bibtex/2555a009db482ff7269d484df80a8a220/brazovayeye},
booktitle = {Proceedings of the Congress on Evolutionary
Computation},
editor = {Angeline, Peter J. and Michalewicz, Zbyszek and Schoenauer, Marc and Yao, Xin and Zalzala, Ali},
interhash = {4eeb112c2d13843b0c3e95f55fcb19e7},
intrahash = {555a009db482ff7269d484df80a8a220},
isbn = {0-7803-5537-7 (Microfiche)},
keywords = {ILP algorithms, data evolutionary genetic inductive language logic mining, natural processing, programming,},
month = {6-9 July},
notes = {CEC-99 - A joint meeting of the IEEE, Evolutionary
Programming Society, Galesia, and the IEE.
Library of Congress Number = 99-61143},
organisation = {Congress on Evolutionary Computation, IEEE / Neural
Networks Council, Evolutionary Programming Society,
Galesia, IEE},
pages = {1338--1346},
publisher = {IEEE Press},
publisher_address = {445 Hoes Lane, P.O. Box 1331, Piscataway, NJ
08855-1331, USA},
timestamp = {2008-06-19T17:50:11.000+0200},
title = {Evolution of Logic Programs: Part-of-Speech Tagging},
url = {http://www.stancomb.co.uk/~prr/Papers/cec99.ps},
volume = 2,
year = 1999
}