The clarity-brevity trade-off in generating referring expressions

Imtiaz Hussain Khan, Graeme D Ritchie, Kees Van Deemter

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

Existing algorithms for the Generation of Referring Expressions (GRE) aim at generating descriptions that allow a hearer to identify its intended referent uniquely; the length of the expression is also considered, usually as a secondary issue. We explore the possibility of making the trade-off between these two factors more explicit, via a general cost function which scores these two aspects separately. We sketch some more complex phenomena which might be amenable to this treatment.
Original languageEnglish
Title of host publicationProceedings of 4th International Conference on Natural Language Generation (INLG2006)
PublisherACL
Pages89-91
Number of pages3
Publication statusPublished - 2006
Event4th International Natural Language Generation Conference (INLG2006) - Sydney, Australia
Duration: 15 Jul 200616 Jul 2006

Conference

Conference4th International Natural Language Generation Conference (INLG2006)
Country/TerritoryAustralia
CitySydney
Period15/07/0616/07/06

Keywords

  • Generation of Referring Expressions

Fingerprint

Dive into the research topics of 'The clarity-brevity trade-off in generating referring expressions'. Together they form a unique fingerprint.

Cite this