Modelling control in generation

Roger Evans, David Weir, John Carroll, Daniel Paiva, Anja Belz

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

Abstract

In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a systematic way. Our approach factors control into two components, a ‘generation tree’ which maps out the relationships between different decisions, and an algorithm for traversing such a tree which determines which choices are actually made. We illustrate the approach with examples of stylistic control and automatic text revision using both generative and empirical techniques. We argue that this approach provides a useful basis for the theoretical study of control in generation, and a framework for implementing generators with a range of control strategies. We also suggest that this approach can be developed into tool for analysing and adapting control aspects of other advanced wide-coverage generation systems.
Original languageEnglish
Title of host publication11th European Workshop on Natural Language Generation (ENLG '07)
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages25-32
Number of pages8
DOIs
Publication statusPublished - 1 Jun 2007
Event11th European Workshop on Natural Language Generation (ENLG '07) - Schloss Dagstuhl, Germany
Duration: 1 Jun 2007 → …

Workshop

Workshop11th European Workshop on Natural Language Generation (ENLG '07)
Period1/06/07 → …

Keywords

  • Natural language generation

Cite this

Evans, R., Weir, D., Carroll, J., Paiva, D., & Belz, A. (2007). Modelling control in generation. In 11th European Workshop on Natural Language Generation (ENLG '07) (pp. 25-32). Stroudsburg, PA, USA: Association for Computational Linguistics. https://doi.org/sro.sussex.ac.uk/id/eprint/30593
Evans, Roger ; Weir, David ; Carroll, John ; Paiva, Daniel ; Belz, Anja. / Modelling control in generation. 11th European Workshop on Natural Language Generation (ENLG '07). Stroudsburg, PA, USA : Association for Computational Linguistics, 2007. pp. 25-32
@inproceedings{181ad4a191a54e7bb99f1058929fa0f2,
title = "Modelling control in generation",
abstract = "In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a systematic way. Our approach factors control into two components, a ‘generation tree’ which maps out the relationships between different decisions, and an algorithm for traversing such a tree which determines which choices are actually made. We illustrate the approach with examples of stylistic control and automatic text revision using both generative and empirical techniques. We argue that this approach provides a useful basis for the theoretical study of control in generation, and a framework for implementing generators with a range of control strategies. We also suggest that this approach can be developed into tool for analysing and adapting control aspects of other advanced wide-coverage generation systems.",
keywords = "Natural language generation",
author = "Roger Evans and David Weir and John Carroll and Daniel Paiva and Anja Belz",
year = "2007",
month = "6",
day = "1",
doi = "sro.sussex.ac.uk/id/eprint/30593",
language = "English",
pages = "25--32",
booktitle = "11th European Workshop on Natural Language Generation (ENLG '07)",
publisher = "Association for Computational Linguistics",

}

Evans, R, Weir, D, Carroll, J, Paiva, D & Belz, A 2007, Modelling control in generation. in 11th European Workshop on Natural Language Generation (ENLG '07). Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 25-32, 11th European Workshop on Natural Language Generation (ENLG '07), 1/06/07. https://doi.org/sro.sussex.ac.uk/id/eprint/30593

Modelling control in generation. / Evans, Roger; Weir, David; Carroll, John; Paiva, Daniel; Belz, Anja.

11th European Workshop on Natural Language Generation (ENLG '07). Stroudsburg, PA, USA : Association for Computational Linguistics, 2007. p. 25-32.

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

TY - GEN

T1 - Modelling control in generation

AU - Evans, Roger

AU - Weir, David

AU - Carroll, John

AU - Paiva, Daniel

AU - Belz, Anja

PY - 2007/6/1

Y1 - 2007/6/1

N2 - In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a systematic way. Our approach factors control into two components, a ‘generation tree’ which maps out the relationships between different decisions, and an algorithm for traversing such a tree which determines which choices are actually made. We illustrate the approach with examples of stylistic control and automatic text revision using both generative and empirical techniques. We argue that this approach provides a useful basis for the theoretical study of control in generation, and a framework for implementing generators with a range of control strategies. We also suggest that this approach can be developed into tool for analysing and adapting control aspects of other advanced wide-coverage generation systems.

AB - In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a systematic way. Our approach factors control into two components, a ‘generation tree’ which maps out the relationships between different decisions, and an algorithm for traversing such a tree which determines which choices are actually made. We illustrate the approach with examples of stylistic control and automatic text revision using both generative and empirical techniques. We argue that this approach provides a useful basis for the theoretical study of control in generation, and a framework for implementing generators with a range of control strategies. We also suggest that this approach can be developed into tool for analysing and adapting control aspects of other advanced wide-coverage generation systems.

KW - Natural language generation

U2 - sro.sussex.ac.uk/id/eprint/30593

DO - sro.sussex.ac.uk/id/eprint/30593

M3 - Conference contribution with ISSN or ISBN

SP - 25

EP - 32

BT - 11th European Workshop on Natural Language Generation (ENLG '07)

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

ER -

Evans R, Weir D, Carroll J, Paiva D, Belz A. Modelling control in generation. In 11th European Workshop on Natural Language Generation (ENLG '07). Stroudsburg, PA, USA: Association for Computational Linguistics. 2007. p. 25-32 https://doi.org/sro.sussex.ac.uk/id/eprint/30593