Entailment due to Syntactically Encoded Semantic Relationships

The majority of the state-of-the-art approaches to recognizing textual entailment focus on defining a generic approach to RTE. A generic approach never works well for every single entailment pair: there are entailment pairs that are recognized poorly by all the generic systems. Automatic identification of such entailment pairs and applying to them an RTE algorithm that is specific to them could thus increase an overall performance of an entailment engine (that in this case will combine a generic RTE algorithm with a number of RTE algorithms for the problematic entailment pairs). We identify one subtype of entailment pairs and develop a two-part probabilistic model for their classification into true and false entailments and evaluate it relative both to a baseline and to the RTE systems. We show that the model performs better than the baseline and the average of the systems from the RTE2 on both the balanced and unbalanced datasets we have created for evaluation.