Show simple item record

dc.contributor.advisorSTD
dc.contributor.authorNickerson, Jill
dc.contributor.authorShieber, Stuart
dc.contributor.authorGrosz, Barbara
dc.date.accessioned2008-11-10T19:57:45Z
dc.date.issued2006
dc.identifier.citationJill Nickerson, Stuart M. Shieber, and Barbara J. Grosz. Referring-expression generation using a transformation-based learning approach. In Proceedings of the 19th International FLAIRS Conference, Melbourne Beach, FL, 11-13 May 2006.en
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:2252608
dc.description.abstractA natural language generation system must generate expressions that allow a reader to identify the entities to which they refer. This paper describes the creation of referring-expression (RE) generation models developed using a transformation-based learning approach. We present an evaluation of the learned models and compare their performance to the performance of a baseline system, which always generates full noun phrase REs. When compared to the baseline system, the learned models produce REs that lead to more coherent natural language documents and are more accurate and closer in length to those that people use.en
dc.description.sponsorshipEngineering and Applied Sciencesen
dc.language.isoen_USen
dc.publisherAssocation for the Advancement of Artifical Intelligenceen
dc.relation.isversionofhttp://www.aaai.org/Library/FLAIRS/2006/flairs06-016.phpen
dash.licenseLAA
dc.titleReferring-expression generation using a transformation-based learning approachen
dc.relation.journalProceedings of the 19th International FLAIRS Conferenceen
dash.depositing.authorShieber, Stuart
dash.identifier.orcid0000-0002-7733-8195*
dash.contributor.affiliatedGoodridge, Andrew
dash.contributor.affiliatedGrosz, Barbara


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record