ABSTRACT
We show the application of an optimisation technique to natural language processing: genetic algorithms, thanks to the definition of a data structure called board and a formal distance. The system has two interesting features: non-directionality, which is more than bidirectionality, and self-assessment, independently of the inner knowledge. Results of experiments are presented and discussed.
- {Boitet and Zaharin 88} Christian Boitet and Zaharin Yusoff Representation trees and string-tree correspondences Proceedings of COLING-88, pp. 59--64, Budapest, 1988. Google ScholarDigital Library
- {Goldberg 89} David E. Goldberg Genetic Algorithms in Search, Optimization, and Machine Learning Addison Wesley Publishing Company, 1989. Google ScholarDigital Library
- {Harrison et al. 91} P. Harrison, S. Abney, E. Black, D. Flickenger, C. Gdaniec, R. Grishman, D. Hindle, R. Ingria, M. Marcus, B. Santorini, T. Strzalkowski Evaluating Syntax Performance of Parser / Grammars of English Proceedings of the Workshop on Evaluating Natural Language Processing Systems, ACL, 1991, pp. ?-?.Google Scholar
- {Furuse and Iida 92b} Furuse Osamu and Iida Hitoshi An Example-based Method for Transfer-driven Machine Translation Proceedings of the fourth International Conference on Theoretical and Methodological Issues in Machine Translation TMI-92, pp. 139--150, Montréal, 1992.Google Scholar
- {Koza 92} John R. Koza Genetic Programming - On the Programming of Computers by Means of Natural Selection MIT Press, 1992. Google ScholarDigital Library
- {Lepage 91} Yves Lepage Parsing and Generating Context-Sensitive Languages with Correspondence Identification Grammars Proceedings of the Pacific Rim Symposium on Natural Language Processing, Singapore, November 1991, pp. 256--263.Google Scholar
- {Lepage et al. 92} Yves Lepage, Furuse Osamu and Iida Hitoshi Relation between a pattern-matching operation and a distance: On the path to reconcile two approaches in Natural Language Proceessing Proceedings of the First Singapore International Conference on Intelligent Systems, Singapore. November 1992, pp. 513--518.Google Scholar
- {Sadler and Vendelmans 90} Victor Sadler and Ronald Vendelmans Pilot implementation of a bilingual knowledge bank Proceedings of Coling-90, Helsinki. 1990, vol 3, pp. 449--451. Google ScholarDigital Library
- {Sato and Nagao 90} Sato Satoshi and Nagao Makoto Toward Memory-based Translation Proceedings of Coling-90, Helsinki, 1990, vol 2, pp. 247--252. Google ScholarDigital Library
- {Selkow 77} Stanley M. Selkow The Tree-to-Tree Editing Problem Information Processing Letters, Vol. 6, No. 6, December 1977, pp. 184--186.Google Scholar
- {Tong 89} Tong Loong Cheong A data-driven control strategy for grammar writing systems Machine Translation, 4(4), December 1989, pp. 177--193.Google Scholar
- {Vauquois and Chappuy 85} Bernard Vauquois and Sylvianc Chappuy Static grammars: a formalism for the description of linguistic models Proceedings of the Conference on Theoretical and Methodological Issues in Machine Translation, Colgate University, Hamilton, New York, August 1985, pp. 298--322.Google Scholar
- {Wagner & Fischer 74} Robert A. Wagner and Michael J. Fischer The String-to-String Correction Problem Journal for the Association of Computing Machinery, Vol. 21, No. 1, January 1974, pp. 168--173. Google ScholarDigital Library
- {Zaharin and Lepage 92} Zaharin Yusoff and Yves Lepage On the specification of abstract linguistic structures in formalisms for Machine Translation Proceedings of the International Symposium on Natural Language Understanding and AI, pp. 145--153, Iizuka, July 1992.Google Scholar
- Non-directionality and self-assessment in an example-based system using genetic algorithms
Recommendations
Genetic operators' significance assessment in multi-population genetic algorithms
Genetic algorithms are widely applied bioinspired optimisation technique that search for a global optimal solution via three main genetic operators, namely selection, crossover, and mutation. In order to determine the operators importance when multi-...
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Learning Intelligent Genetic Algorithms Using Japanese Nonograms
An intelligent genetic algorithm (IGA) is proposed to solve Japanese nonograms and is used as a method in a university course to learn evolutionary algorithms. The IGA combines the global exploration capabilities of a canonical genetic algorithm (CGA) ...
Comments