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 ISBNResearchpeer-review

Abstract

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
Pages58-65
Number of pages8
Publication statusPublished - Jun 2005
EventProceedings of the 43rd Annual Meeting of the ACL - Ann Arbor, USA
Duration: 1 Jun 2005 → …

Conference

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

Bibliographical note

Creative Commons Attribution-ShareAlike License

Keywords

  • Natural language generation

Cite this

Paiva, D., & Evans, R. (2005). Empirically-based control of natural language generation. In Proceedings of the 43rd Annual Meeting of the ACL (pp. 58-65). Association for Computational Linguistics.
Paiva, Daniel ; Evans, Roger. / Empirically-based control of natural language generation. Proceedings of the 43rd Annual Meeting of the ACL. Association for Computational Linguistics, 2005. pp. 58-65
@inproceedings{ddccfa9c2a914b9ea8cbf3ace81cada5,
title = "Empirically-based control of natural language generation",
abstract = "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.",
keywords = "Natural language generation",
author = "Daniel Paiva and Roger Evans",
note = "Creative Commons Attribution-ShareAlike License",
year = "2005",
month = "6",
language = "English",
pages = "58--65",
booktitle = "Proceedings of the 43rd Annual Meeting of the ACL",
publisher = "Association for Computational Linguistics",

}

Paiva, D & Evans, R 2005, Empirically-based control of natural language generation. in Proceedings of the 43rd Annual Meeting of the ACL. Association for Computational Linguistics, pp. 58-65, Proceedings of the 43rd Annual Meeting of the ACL, 1/06/05.

Empirically-based control of natural language generation. / Paiva, Daniel; Evans, Roger.

Proceedings of the 43rd Annual Meeting of the ACL. Association for Computational Linguistics, 2005. p. 58-65.

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

TY - GEN

T1 - Empirically-based control of natural language generation

AU - Paiva, Daniel

AU - Evans, Roger

N1 - Creative Commons Attribution-ShareAlike License

PY - 2005/6

Y1 - 2005/6

N2 - 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.

AB - 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.

KW - Natural language generation

M3 - Conference contribution with ISSN or ISBN

SP - 58

EP - 65

BT - Proceedings of the 43rd Annual Meeting of the ACL

PB - Association for Computational Linguistics

ER -

Paiva D, Evans R. Empirically-based control of natural language generation. In Proceedings of the 43rd Annual Meeting of the ACL. Association for Computational Linguistics. 2005. p. 58-65