The Google Similarity Distance
Rudi Cilibrasi and Paul Vitányi
IEEE Transactions on Knowledge and Data Engineering 2007.

Abstract

We present a new theory of similarity between words and phrases based on information distance and Kolmogorov complexity. To fix thoughts we use the world wide web as a data base, and Google as a search engine. The method is then appplied to automatically extract similarity, the Google similarity distance, of words and phrases from the Google web page counts.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]