Structured document labeling and rule extraction using a new recurrent fuzzy-neural system

Proposes an approach to the problem of logical labeling in structured documents, employing a new recurrent neuro-fuzzy system called RFasArt (Recurrent Fuzzy Adaptive System, ART-based). RFasArt preserves the fine characteristics, such as modularity, stability and flexibility, of its predecessors Fuzzy ARTMAP and FasArt. In this paper, the documents are considered as pseudo-temporal sequences, and context information is exploited in an integrated form. Two working prototypes for a MIME-based mailing system and for a digital library were tested with over 90% of the recognition rate and less ambiguous decisions than in the previous systems. A manageable knowledge base was constructed using fuzzy rules that were easily interpretable by human users, and examples of rule creation and fusion are shown.