... yxiniixyssnyyxxr)1())((1−−−=∑= (6) Where x and y are the sample means of xi and yi, and sx and sy are sample standard deviations of xi and yi and n is total samples. Most approaches (Resink, 1995; Lin, ... f(Y@X)=0 or f(X@Y)=0, CODC(X,Y)=0; and when f(Y@X)=f(X) and f(X@Y)=f(Y), CODC(X,Y)=1. In the first case, X and Y are of no association. In the second case, X and Y are of the strongest association. ... granularity like terms and documents. Rodríguez and Egenhofer (2003) compute the semantic 1009similarity from WordNet and SDTS ontology by word matching, feature matching and semantic neighborhood...