International Business Machines Corporation
Document quality inspection

Abstract:

Methods, computer systems, and computer program products are provided for generating one or more condition sets from one or more documents. The method includes recognizing one or more paragraphs in each document having one or more listing and nested paragraphs and generating one or more paragraph trees wherein each node in the paragraph tree corresponds to a paragraph text in the document. The method further includes extracting one or more conditions as a logical formula from each paragraph text comprising a condition expression; and obtaining one or more condition sets written by a set of logical formulas from the one or more extracted conditions, according to a set of child nodes belonging to each common parent node in each of the paragraph trees; generating one condition set used for quality inspection, for each of the one or more condition sets written by the set of logical formulas.