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.