Using discourse commitments to recognize textual entailment

Abstract

In this paper, we introduce a new framework for recognizing textual entailment (RTE) which depends on extraction of the set of publicly-held beliefs - known as discourse commitments - that can be ascribed to the author of a text (t) or a hypothesis (h). We show that once a set of commitments have been extracted from a t-h pair, the task of recognizing textual entailment is reduced to the identification of the commitments from at which support the inference of the h. Our system correctly identified entailment relationships in more than 80% of t-h pairs taken from all three of the previous PASCAL RTE Challenges, without the need for additional sources of training data. © 2008 Licensed under the Creative Commons.