Abstract

Knowledge bases open new horizons for machine learning research. One challenge is to design learning programs to expand the knowledge base using the knowledge that is currently available. This paper addresses the problem of discovering regularities in large knowledge bases that contain many assertions in different domains. The paper begins with a definition of regularities and gives the motivation for such a definition. It then outlines a framework that attempts to integrate induction with knowledge. Although the implementation of the framework currently uses only a statistical method for confirming hypotheses, its application to some real knowledge base has shown some encouraging and interesting results. 1 Introduction Discovering regularities from knowledge bases is an important problem for both Knowledge Engineering and Machine Learning. Since the task is aimed at generating new knowledge, its success will directly contribute to knowledge acquisition and the construction of large k...

Citations