A neural cascade architecture for document retrieval

Author

Bouchachia, Abdelhamid ; Mittermeir, Roland

Author_Institution

Dept. of Inf.-Syst., Klagenfurt Univ., Austria

Volume

3

fYear

2003

fDate

20-24 July 2003

Firstpage

1915

Abstract

This paper describes a fuzzy neural approach adopted for information retrieval. After a thematic analysis of documents that produces two conceptual sets called themes and rhemes, a fuzzy representation is derived. The fuzzy representation reflects the hierarchical nature of texts and suggests the use of type-2 fuzzy sets. It is then translated into a cascade of two neural networks. The first level in this cascade is a fuzzy associative memory network (FAM) which maps rhemes to themes and the second level consists of a fuzzy adaptive resonance theory network (Fuzzy ART) which relates themes to document categories. The approach was experimentally evaluated.

Keywords

ART neural nets; content-addressable storage; fuzzy neural nets; fuzzy set theory; information retrieval; document retrieval; document thematic analysis; fuzzy adaptive resonance theory network; fuzzy associative memory network; fuzzy neural approach; fuzzy representation; fuzzy set theory; information retrieval; neural cascade architecture; neural networks; Competitive intelligence; Computational intelligence; Fuzzy neural networks; Fuzzy sets; Information retrieval; Intelligent agent; Natural language processing; Neural networks; Optical computing; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223700

Filename

1223700