Algorithms for generating referring expressions: Do they do what people do?

Jette Viethen*, Robert Dale

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

26 Citations (Scopus)

Abstract

The natural language generation literature provides many algorithms for the generation of referring expressions. In this paper, we explore the question of whether these algorithms actually produce the kinds of expressions that people produce. We compare the output of three existing algorithms against a data set consisting of human-generated referring expressions, and identify a number of significant differences between what people do and what these algorithms do. On the basis of these observations, we suggest some ways forward that attempt to address these differences.

Original languageEnglish
Title of host publicationCOLING/ACL 2006: INLG-06 - 4th International Natural Language Generation Conference, Proceedings of the Conference
EditorsNathalie Colineau, Cecile Paris, Stephen Wan, Robert Dale
Place of PublicationStroudsburg, USA
PublisherAssociation for Computational Linguistics (ACL)
Pages63-72
Number of pages10
ISBN (Print)1932432728, 9781932432725
Publication statusPublished - 2006
Event4th International Natural Language Generation Conference, INLG-06 - Sydney, NSW, Australia
Duration: 15 Jul 200616 Jul 2006

Other

Other4th International Natural Language Generation Conference, INLG-06
CountryAustralia
CitySydney, NSW
Period15/07/0616/07/06

Fingerprint

Dive into the research topics of 'Algorithms for generating referring expressions: Do they do what people do?'. Together they form a unique fingerprint.

Cite this