PRISM: A Language for Symbolic-Statistical Modeling

We present an overview of symbolic-statistical modeling language PRISM whose programs are not only a probabil istic extension of logic programs but also able to learn f rom examples w i th the help of the EM learning algori thm. As a knowledge representation language appropriate for probabil istic reasoning, it can describe various types of symbolic-statistical modeling formalism known but unrelated so far in a single framework. We show by examples, together w i th learning results, that most popular probabil istic modeling formalisms, the hidden Markov model and Bayesian networks, are described by PR ISM programs.