Generating Easy References: the case of document deixis.

Ivandre Paraboni, Kees van Deemter

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

Abstract

This paper argues that algorithms for the
generation of referring expressions should
aim to make it easy for hearers and readers
to find the referent of the expressions that
are generated. To illustrate this claim, an
algorithm is described for the generation
of expressions that refer across a hierarchically ordered domain, and which takes
search effort into account by adding logically redundant information. To support
the ideas underlying the algorithm, a psycholinguistic experiment is presented that
confirms readers’ preference for the generated, logically redundant expressions
over non-redundant alternatives.
Original languageEnglish
Title of host publicationProceedings of Second International Natural Language Generation Conference (INLG-2002)
EditorsKathleen McKeown
PublisherAssociation for Computational Linguistics (ACL)
Pages113-119
Number of pages7
Publication statusPublished - 2002
Event2nd International Natural Language Generation Conference - Harriman, United States
Duration: 1 Jul 20023 Jul 2002
https://aclanthology.org/volumes/W02-21/

Conference

Conference2nd International Natural Language Generation Conference
Abbreviated titleINGL 2002
Country/TerritoryUnited States
CityHarriman
Period1/07/023/07/02
Internet address

Keywords

  • Generation of Referring Expressions

Fingerprint

Dive into the research topics of 'Generating Easy References: the case of document deixis.'. Together they form a unique fingerprint.

Cite this