| 摘要 |
<P>PROBLEM TO BE SOLVED: To respond to the problem in which all words present in an associative term dictionary must be found out from a text including notation variability, whereas it is demanded in biomedical field to automatically extract knowledge of a technical term by extracting words corresponding to the preliminarily arranged associative term dictionary followed by document analysis or to perform static analysis related to medical insurance by extracting words corresponding to a medical action master from medical fee bills and, in general, the text thereof frequently includes notation variability such as difference in word order, typing error, reading mistake or non-reading. <P>SOLUTION: Valid graphs are formed from partial character strings of an associative term, and a combination of partial character strings covering the text at a minimum cost is selected. According to this, all words present in the associative term dictionary can be found out from the test including notation variability by erroneous reading, non-reading, typing error, or dislocation of word unit. <P>COPYRIGHT: (C)2007,JPO&INPIT |
