Acquiring and using limited user models in NLG

Research output: Contribution to conferenceUnpublished paperpeer-review

9 Citations (Scopus)

Abstract

It is a truism of NLG that good knowledge of the reader can improve the quality of generated texts, and many NLG systems have been developed that exploit detailed user models when generating texts. Unfortunately, it is very difficult in practice to obtain detailed information about users. In this paper we describe our experiences in acquiring and using limited user models for NLG in four different systems, each of which took a different approach to this issue. One general conclusion is that it is useful if imperfect user models are understandable to users or domain experts, and indeed perhaps can be directly edited by them; this agrees with recent thinking about user models in other applications such as intelligent tutoring systems (Kay, 2001).

Original languageEnglish
Pages87-94
Number of pages8
Publication statusPublished - 2003
Event9th European Workshop on Natural Language Generation, ENLG@EACL 2003 - Budapest, Hungary
Duration: 13 Apr 200314 Apr 2003

Conference

Conference9th European Workshop on Natural Language Generation, ENLG@EACL 2003
Country/TerritoryHungary
CityBudapest
Period13/04/0314/04/03

Bibliographical note

Publisher Copyright:
© 2003 European Workshop on Natural Language Generation.

Fingerprint

Dive into the research topics of 'Acquiring and using limited user models in NLG'. Together they form a unique fingerprint.

Cite this