The Second PASCAL Recognising Textual Entailment Challenge

This paper describes the Second PASCAL Recognising Textual Entailment Challenge (RTE-2). 1 We describe the RTE2 dataset and overview the submissions for the challenge. One of the main goals for this year’s dataset was to provide more “realistic” text-hypothesis examples, based mostly on outputs of actual systems. The 23 submissions for the challenge present diverse approaches and research directions, and the best results achieved this year are considerably higher than last year’s state of the art.