WHU at TAC 2009: A Tri-categorization Approach to Textual Entailment Recognition

This paper describes our system of recognizing textual entailment for RTE-5 challenge at TAC 2009. We propose a textual entailment recognition framework and implement a system of classification which takes lexical, syntactic and semantic features as considered. To improve the performance, some lexical-semantic resources and web knowledge bases are also incorporated in the system. Official results show that our system achieves a medium performance of all participating systems.