Explorative multilingual text retrieval based on fuzzy multilingual keyword classification

This paper proposes an explorative approach to multilingual text retrieval (MLTR) based on fuzzy multilingual keyword classification. The approach applies fuzzy clustering to obtain a classification of multilingual keywords by concepts. A multilingual concept directory is developed by labeling each concept with native language of the target user and associating it with relevant multilingual documents. The directory works as a searching interface for document browsing. This explorative approach is particularly suitable for casual users to search with Asian languages by avoiding the trouble of query formulation and input in MLTR. For the general application of MLTR, an explorative interface is also advisable when the user has only a vague idea of the domain to be searched.