Knowledge discovering for document classification using tree matching in TEXPROS

This paper describes a knowledge-based system for classifying documents based upon the layout structure and conceptual information extracted from their contents. The spatial elements in a document are laid out in rectangular blocks which are represented by nodes in an ordered labeled tree, called the "Layout Structure Tree" (L-S Tree). Each leaf node of an L-S Tree points to its corresponding block content. A Knowledge Acquisition Tool (KAT) is devised to perform the inductive learning from L-S Trees of document samples, and then generate the Document Sample Tree and Document Type Tree bases. A testing document is classified if a Document Type Tree is discovered as a substructure of the L-S Tree of the testing document. Then we match the L-S Tree with the Document Sample Trees of the classified document type to find the format of the testing document. The Document Sample Trees and Document Type Trees are called Structural Knowledge Base (SKB). The tree discovering and matching processes involve comparing the SKB trees and a testing document's L-S Tree by using pattern matching and discovering toolkits. Our experimental results demonstrate that many office documents can be classified correctly using the proposed approach.