RHB+: A Type-Oriented ILP System Learning from Positive Data

This paper presents the type-oriented relational learner R H B + . Attaching type information to hypotheses is effective in avoiding overgeneralization as well as enhancing readabili ty and comprehensibility. In many areas, such as NLP, type information is actually available, while negative examples are not. Unfortunately, learning performance is usually poor if types are attached when only positive examples are available. RHB+ makes use of type information to efficiently compute informativi ty from positive examples only and to judge a stopping condition. The new technique of dynamic type restriction by positive examples lets covered positive examples decide the types appropriate for the current clause. The current version of RHB+, written in the typed logic programming language L IFE , directly manipulates types as structured background knowledge when operations related to types are required. These features make RHB+ efficient and effective in attaching types selected from thousands of possible types. This leads to advantages over several previous learners, such as F O I L and P R O G O L . Experimental results demonstrate RHB+ 's fine performance for both artificial and real data.