A Genetic Algorithm to Improve Agent-Oriented Natural Language Interpreters

Babak Hodjat¹, Junichi Ito¹, and Makoto Amamiya²

¹Dejima Inc., USA
Babak@dejima.com
junichi.ito@dejima.com
www.dejima.com

²Kyushu University, Japan
amamiya@is.kyushu-u.ac.jp

Abstract. A genetic algorithm is used to improve the success-rate of an AAOSA-based application. Tests show promising results both in the improvement made in the success-rate of the development and test corpora, and in the nature and number of interpretation rules added to agents.

Keywords: Agent-Oriented Software Engineering, Evolutionary Optimization, GA, Natural Language Interfaces.

LNCS 3103, p. 1307 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004