Two Related Lexico-Syntactic Approaches to Entailment

Two approaches to Textual Entailment are presented. They both rely on lexico-syntactic information. The two approaches differ mainly in the way the syntactic relationships are derived. In one approach, the syntactic relationships are drawn from a phrase-based parse tree. In the other, we use information provided by a dependency parser. The first approach performs at 0.59 precision and 0.6047 average precision. The second system´s performance is 0.5837 precision and 0.5785 average precision.