Abstract

A content processing system determines the content of input discourse. The content processing system includes a lexicon, which contains definitional characteristics for words and terms, and a knowledge catalog. The knowledge catalog provides independent and parallel static ontologies to accurately represent a broad coverage of concepts that define knowledge. The knowledge catalog also includes a dynamic level for expanding concepts in the static ontologies. A theme parsing system determines the thematic context of input discourse including identifying the topics of the discourse, generating summarized versions of the discourse, and identifying the key content of the discourse. A knowledge catalog processor processes the extracted content for use with the knowledge catalog. A theme vector processor identifies the most important themes in the input discourse, and maps these themes into the knowledge catalog. The content indexing processor extends the static ontologies into the dynamic level based on the specific terminology contained in the input discourse, and attaches the dynamic level into concepts in the static ontologies that were mapped by the theme vector processor.