Unsupervised language independent genetic algorithm approach to trivial dialogue phrase generation and evaluation

Authors:
Calkin S. Montero;Kenji Araki
Affiliations:
Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan;Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan
Venue:
NLDB'07 Proceedings of the 12th international conference on Applications of Natural Language to Information Systems
Year:
2007

Citing 3
Cited 1

Learning syntactic rules and tags with genetic algorithms for information retrieval and filtering: an empirical basis for grammatical rules

Information Processing and Management: an International Journal
WebGALAXY: beyond point and click—a conversational interface to a browser

Selected papers from the sixth international conference on World Wide Web
ELIZA—a computer program for the study of natural language communication between man and machine

Communications of the ACM

Evaluation of Trivial Dialogue Phrase Databases Through Practical Application to User-Computer Conversation - Case Study: English - Spanish

KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an ongoing work on the generation and the automatic evaluation of trivial dialogue phrases. The described system uses a genetic algorithm (GA)-like transfer approach and n-grams frequency information obtained from the Web in order to automatically generate and evaluate phrases. The experiments present promising results, showing to achieve 78.51% of the user understandability of the generated and evaluated good phrases for English, and 79.06% for Spanish, and indicating the portability of the approach.