Learning First-Order Acyclic Horn Programs from Entailment

Chandra Reddy, Prasad Tadepalli

Abstract: In this paper, we consider learning first-order Horn programs from entailment. In particular, we show that any subclass of first-order acyclic Horn programs with constant arity is exactly learnable from equivalence and entailment membership queries provided it allows a polynomial-time subsumption procedure and satisfies some closure conditions. One consequence of this is that first-order acyclic determinate Horn programs with constant arity are exactly learnable from equivalence and entailment membership queries.