ICML-98 Submission #37

Title: 
        An Information-Theoretic Definition of Similarity

Authors with addresses:
        Dekang Lin
        Department of Computer Science, University of Manitoba
        Winnipeg, Manitoba, Canada, R3T, 2N2

Abstract (250 word maximum):
  Similarity is an important and widely used
  concept. Previous definitions of similarity are tied to a particular
  application or a form of knowledge representation. We present an
  information-theoretic definition of similarity that is applicable as
  long as there is a probabilistic model.  We demonstrate how our
  definition can be used to measure the similarity in a number of
  different domains.

Keywords:
        similarity, natural language learning

Email address of contact author:
        lindek@cs.umanitoba.ca

Phone number of contact author:
        (204) 474-9740