TBL Template Selection: An Evolutionary Approach

Authors:
Ruy Luiz Milidiú;Julio Cesar Duarte;Cícero Nogueira Dos Santos
Affiliations:
Departamento de Informática, Pontifícia Universidade Católica, Rio de Janeiro, Brazil;Centro Tecnológico do Exército, Rio de Janeiro, Brazil;Departamento de Informática, Pontifícia Universidade Católica, Rio de Janeiro, Brazil
Venue:
Current Topics in Artificial Intelligence
Year:
2007

Citing 5
Cited 0

Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

Computational Linguistics
Shallow parsing with pos taggers and linguistic features

The Journal of Machine Learning Research
A rule-based approach to prepositional phrase attachment disambiguation

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Use of a genetic algorithm in brill's transformation-based part-of-speech tagger

GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Constrained atomic term: widening the reach of rule templates in transformation based learning

EPIA'05 Proceedings of the 12th Portuguese conference on Progress in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Transformation Based Learning (TBL) is an intensively Machine Learning algorithm frequently used in Natural Language Processing. TBL uses rule templates to identify error-correcting patterns. A critical requirement in TBL is the availability of a problem domain expert to build these rule templates. In this work, we propose an evolutionary approach based on Genetic Algorithms to automatically implement the template selection process. We show some empirical evidence that our approach provides template sets with almost the same quality as human built templates.