A Confidence Model for Syntactically-Motivated Entailment Proofs

This paper presents a novel method for recognizing textual entailment which derives the hypothesis from the text through a sequence of parse tree transformations. Unlike related approaches based on tree-edit-distance, we employ transformations which better capture linguistic structures of entailment. This is achieved by (a) extending an earlier deterministic knowledge-based algorithm with syntactically-motivated on-the-fly transformations, and (b) by introducing an algorithm that uniformly learns costs for all types of transformations. Our evaluations and analysis support the validity of this approach.