Human and machine generated knowledge have different strengths and weaknesses. Human knowledge isrnprecise but has often limited coverage. Machine generated knowledge is less precise but can cover morernground efficiently. Knowledge based systems should tightly integrate both. Unfortunately, only few ways ofrncombining human and machine generated knowledge will be practical and efficient. Three such knowledgernintegration approaches are developed and tested: human judgments to guide probabilistic and evolutionaryrninformation retrieval techniques, ontologies to provide the semantic context for an automatically createdrnthesaurus, and ontologies to augment natural language processing. Human generated, precise, domain-specificrnontologies were found to be well suited for integration with both machine learning algorithms and naturalrnlanguage processing for knowledge discovery. These conclusions are applied in the development of GeneScene,rna knowledge based system being developed for biomedicine. GeneScene relies on a novel natural languagernprocessing technique: a 'function word'-based parser. This parser is integrated with medical ontologies tornextract biomedical pathway information from text.
展开▼
