Knowledge discovery and data mining to assist natural language understanding.

摘要: As natural language processing systems become more frequent in clinical use, methods for interpreting the output of these programs increasingly important. These require effort a domain expert, who must build specific queries and rules processor output. Knowledge discovery data mining tools can be used instead expert to automatically generate rules. C5.0, decision tree generator, was create rule base understanding system. A general-purpose using this tested on set 200 chest radiograph reports. When small reports, classified by physicians, as training set, generated performed well lay persons, but worse than physicians. larger ICD9 coding classify system, physicians persons. It appears that larger, accurate is needed increase performance method.