{"title":"A Discourse Commitment-Based Framework for Recognizing Textual Entailment","authors":"Andrew Hickl, Jeremy Bensley","doi":"10.3115/1654536.1654571","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":190678,"journal":{"name":"ACL-PASCAL@ACL","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"92","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACL-PASCAL@ACL","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3115/1654536.1654571","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 92
Abstract
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.