In 2008 the Recognizing Textual Entailment Challenge (RTE-4) was proposed for the first time as a track at the Text Analysis Conference (TAC). Another important innovation introduced in this campaign was a three-judgment task, which required the systems to make a further distinction between pairs where the entailment does not hold because the content of H is contradicted by the content of T, and pairs where the entailment cannot be determined because the truth of H cannot be verified on the basis of the content of T. A classic two-way task was also offered. RTE-4 attracted 26 teams, more than half of whom submitted runs for the new 3-way task. This paper describes the preparation of the dataset, and gives an overview of the results achieved by the participating systems.
展开▼
