A Discourse Commitment-Based Framework for Recognizing Textual Entailment

In this paper, we introduce a new framework for recognizing textual entailment 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 or a hypothesis. 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 a t which support the inference of the h. Promising results were achieved: our system correctly identified more than 80% of examples from the RTE-3 Test Set correctly, without the need for additional sources of training data or other web-based resources.