An Abduction framework for Handling Incompleteness in First-Order Learning

This paper presents the ILP incremental learning system INTHELEX, focusing on its abductive capability. It is based on an abductive proof procedure that aims at attacking the problem of incomplete information by hypothesizing likely facts that are not explicitly stated in the observations. The system implements a framework in which inductive and abductive inference been brought to cooperation, and its performance in experiments on both artificial and real-world dataset is encouraging.