Mutual Information or MI score is widely used as the statistical measure of collocation in linguistic studies. The number of bits of "shared information" between two words can be calculated by observed co-occurrence ( O ) and expected co-occurrence ( E ). MI = log 2 (O/E) The MI score , then, is implemented as cut-off threshold for collocate selection. I n practical applications, however, MI was found to have a tendency to assign inflated scores to low-frequency word pair with E << 1 , especially for data from large corpora. Thus, even a single concurrence of two word types might result in a fairly high association score (see Evert's Extended manuscript of orpora and collocations ). Multiplication with O is used to increase the influence of observed concurrence frequency compared to the expected, result in the formula log 2 (O k /E) with k >= 1 (the well known MI k family).