Deciding Entailment and Contradiction with Stochastic and Edit Distance-based Alignment.

Abstract

Analysis stage. Our goal at this stage is to compute linguistic representations of the passage and the hypothesis that contain as much information as possible about their semantic content. We use typed dependency graphs generated by the Stanford parser (Klein and Manning, 2003; de Marneffe et al., 2006), which contain a node for each word and labeled edges representing the grammatical relations between words. Named entities are identified by a CRF-based NER system, and contiguous collocations which appear in WordNet are collapsed.