Inverse document frequency (IDF) A measure of deviations from Poisson.pdfVIP

Inverse Document Frequency (IDF): A Measure of Deviations from Poisson Kenneth W. Church William A. Gale ATT Bell Laboratories Murray Hill, NJ, USA 07974 kwc@ Abstract Low frequency words tend to be rich in content, and vice versa. But not all equally frequent words are equally meaningful. We will use inverse document frequency (IDF), a quantity borrowed from Information Retrieval, to distinguish words like somewhat and boycott. Both somewhat and boycott appeared approximately 1000 times in a corpus of 1989 Associated Press articles, but boycott is a better keyword because its IDF is farther from what would be expected by chance (Poisson). 1. Document frequency is similar to word frequency, but different Word frequency is commonly used in all sorts of natural language applications. The practice implicitly assumes that words (and ngrams) are distributed by a single parameter distribution such as a Poisson or a Binomial. But we find that these distributions do not fit the data very well. Both the Poisson and Binomial assume that the variance over documents is no larger than the mean, and yet, we find that it can be quite a bit larger, especially for interesting words such as boycott where there are hidden variables such as topic that conspire to undermine the independence assumption behind the Poisson and the Binomial. Much better fits are obtained by introducing a second parameter such as inverse document frequency (IDF). Inverse document frequency (IDF) is commonly used in Information Retrieval (Sparck Jones, 1972). IDF is defined as ? log 2 df w / D, where D is the number of documents in the collection and df w is the document frequency, the number of documents that contain w. Obviously, there is a strong relationship between document frequency, df w , and word frequency, f w . The relationship is shown in Figure 1, a plot of log 10 f w and IDF for 193 words selected from a 50 million word corpus of 1989 Associated Press (AP) Newswire stories (D = 85 , 432 stories)