This research improves the precision of information extraction from free-form text via the use of cognitive-based approaches to natural language processing (NLP). Cognitive-based approaches are an important, and relatively new, area of research in NLP and search, as well as linguistics. Cognitive approaches enable significant improvements in both the breadth and depth of knowledge extracted from text. This research has made contributions in the areas of a cognitive approach to automated concept recognition in. Cognitive approaches to search, also called concept-based search, have been shown to improve search precision. Given the tremendous amount of electronic text generated in our digital and connected world, cognitive approaches enable substantial opportunities in knowledge discovery. The generation and storage of electronic text is ubiquitous, hence opportunities for improved knowledge discovery span virtually all knowledge domains. While cognition-based search offers superior approaches, challenges exist due to the need to mimic, even in the most rudimentary way, the extraordinary powers of human cognition. This research addresses these challenges in the key area of a cognition-based approach to automated concept recognition. In addition it resulted in a semantic processing system framework for use in applications in any knowledge domain. Confabulation theory was applied to the problem of automated concept recognition. This is a relatively new theory of cognition using a non-Bayesian measure, called cogency, for predicting the results of human cognition. An innovative distance measure derived from cogent confabulation and called inverse cogency, to rank order candidate concepts during the recognition process. When used with a multilayer perceptron, it improved the precision of concept recognition by 5% over published benchmarks. Additional precision improvements are anticipated. These research steps build a foundation for cognition-based, high-precision text mining. Long-term it is anticipated that this foundation enables a cognitive-based approach to automated ontology learning. Such automated ontology learning will mimic human language cognition, and will, in turn, enable the practical use of cognitive-based approaches in virtually any knowledge domain. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://bibliotheek.ehb.be:2222/en-US/products/dissertations/individuals.shtml.]