Starting with scanned image(s) of a document's pages (either from hardcopy or from a fax source), the authors attempt to produce document representations which can be stored in a database which then supports a variety of document understanding applications. Current work to develop an intelligent document understanding system prototype, aimed towards this goal, is described.>

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called probabilistic prediction to predict which grammar rules are likely to lead to an acceptable parse of the input. Using a suboptimal search method, Picky significantly reduces the number of edges produced by CKY-like chart parsing algorithms, while maintaining the robustness of pure bottom-up parsers and the accuracy of existing probabilistic parsers. Experiments using Picky demonstrate how probabilistic modelling can impact upon the efficiency, robustness and accuracy of a parser.