Interactive query suggestion in Thai library automation system

Abstract

This paper introduces interactive query expansion for Thai library automation system. The approach aims to expand original Thai-language user queries to a new set of more meaningful queries in the same language. The purpose is to improve the quality of Thai user query and suggest the user with a new set of more meaningful queries. User satisfaction with retrieved results should be improved. The approach employs the information in MARC 21 bibliographic format (title access field 245) in order to generate a new list of candidate terms. The genetic process is then augmented to select new expanded terms from those candidates. The approach is evaluated on the collection of Thai educational materials such as book, journal and magazine. The performance is measured by the accuracy of new expanded terms. We asked 87 participants whether our generated terms are related to their original query. The experiment shows that users quite agree that our technique is able to generate useful terms for searching their materials in library system.