Empirically-based control of natural language generation

Daniel Paiva, Roger Evans

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNpeer-review


In this paper we present a new approach to controlling the behaviour of a natural language generation system by correlating internal decisions taken during free generation of a wide range of texts with the surface stylistic characteristics of the resulting outputs, and using the correlation to control the generator. This contrasts with the generate-and-test architecture adopted by most previous empirically-based generation approaches, offering a more efficient, generic and holistic method of generator control. We illustrate the approach by describing a system in which stylistic variation (in the sense of Biber (1988)) can be effectively controlled during the generation of short medical information texts.
Original languageEnglish
Title of host publicationProceedings of the 43rd Annual Meeting of the ACL
PublisherAssociation for Computational Linguistics
Number of pages8
Publication statusPublished - Jun 2005
EventProceedings of the 43rd Annual Meeting of the ACL - Ann Arbor, USA
Duration: 1 Jun 2005 → …


ConferenceProceedings of the 43rd Annual Meeting of the ACL
Period1/06/05 → …

Bibliographical note

Creative Commons Attribution-ShareAlike License


  • Natural language generation

Cite this