A method for information retrieval that matches occurrences of concepts in
natural language text documents against descriptions of concepts in user
queries. Said method, implemented in a computer system, includes a
preferred version of the method that comprises (1) annotating natural
language text in documents and other text-forms with linguistic
information and Concepts and Concept Rules expressed in a Concept
Specification Language (CSL) for a particular domain, (2) pruning and
optimizing synonyms for a particular domain, (3) defining and learning
said CSL Concepts and Concept Rules, (4) checking user-defined
descriptions of Concepts represented in CSL (including user queries), and
(5) retrieval by matching said user-defined descriptions (and queries)
against said annotated text. CSL is a language for expressing
linguistically-based patterns. Said patterns can represent the linguistic
manifestations of concepts in text. Said concepts may derive from the
sublanguages used by experts to analyze specialized domains including,
but not limited to, insurance claims, police incident reports medical
reports, and aviation incident reports.