What is NLG?

Roger Evans, P. Piwek, Lynne Cahill

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

Abstract

Giving an adequate general definition of the input to natural language generation (NLG), and hence to NL G itself, is a notoriously difficult problem, practically, theoretically and even methodologically. In this paper, we describe our recent experiences of implementing an NL G component of a larger question-answering system, and trying to understand and resolve some of these problems in this context. We examine the whole lifetime of an answer, from internal data structure to final expression as text, and look for characteristics of the processing which might help identify where NL G really begins. On the basis of this analysis we propose some principles to inform discussions on the scope of NL G as an individuated enterprise.
Original languageEnglish
Title of host publicationProceedings of the Second International Conference on Natural Language Generation
PublisherAssociation for Computational Linguistics
Pages144-151
Number of pages8
Publication statusPublished - 2002
EventProceedings of the Second International Conference on Natural Language Generation - New York, USA
Duration: 1 Jan 2002 → …

Conference

ConferenceProceedings of the Second International Conference on Natural Language Generation
Period1/01/02 → …

Fingerprint

Data structures
Processing
Industry

Bibliographical note

Creative Commons Attribution Share-Alike License

Keywords

  • Natural language generation
  • NLG

Cite this

Evans, R., Piwek, P., & Cahill, L. (2002). What is NLG? In Proceedings of the Second International Conference on Natural Language Generation (pp. 144-151). Association for Computational Linguistics.
Evans, Roger ; Piwek, P. ; Cahill, Lynne. / What is NLG?. Proceedings of the Second International Conference on Natural Language Generation. Association for Computational Linguistics, 2002. pp. 144-151
@inproceedings{d04a17f1aac44295a2f9f6e3c56eca6b,
title = "What is NLG?",
abstract = "Giving an adequate general definition of the input to natural language generation (NLG), and hence to NL G itself, is a notoriously difficult problem, practically, theoretically and even methodologically. In this paper, we describe our recent experiences of implementing an NL G component of a larger question-answering system, and trying to understand and resolve some of these problems in this context. We examine the whole lifetime of an answer, from internal data structure to final expression as text, and look for characteristics of the processing which might help identify where NL G really begins. On the basis of this analysis we propose some principles to inform discussions on the scope of NL G as an individuated enterprise.",
keywords = "Natural language generation, NLG",
author = "Roger Evans and P. Piwek and Lynne Cahill",
note = "Creative Commons Attribution Share-Alike License",
year = "2002",
language = "English",
pages = "144--151",
booktitle = "Proceedings of the Second International Conference on Natural Language Generation",
publisher = "Association for Computational Linguistics",

}

Evans, R, Piwek, P & Cahill, L 2002, What is NLG? in Proceedings of the Second International Conference on Natural Language Generation. Association for Computational Linguistics, pp. 144-151, Proceedings of the Second International Conference on Natural Language Generation, 1/01/02.

What is NLG? / Evans, Roger; Piwek, P.; Cahill, Lynne.

Proceedings of the Second International Conference on Natural Language Generation. Association for Computational Linguistics, 2002. p. 144-151.

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

TY - GEN

T1 - What is NLG?

AU - Evans, Roger

AU - Piwek, P.

AU - Cahill, Lynne

N1 - Creative Commons Attribution Share-Alike License

PY - 2002

Y1 - 2002

N2 - Giving an adequate general definition of the input to natural language generation (NLG), and hence to NL G itself, is a notoriously difficult problem, practically, theoretically and even methodologically. In this paper, we describe our recent experiences of implementing an NL G component of a larger question-answering system, and trying to understand and resolve some of these problems in this context. We examine the whole lifetime of an answer, from internal data structure to final expression as text, and look for characteristics of the processing which might help identify where NL G really begins. On the basis of this analysis we propose some principles to inform discussions on the scope of NL G as an individuated enterprise.

AB - Giving an adequate general definition of the input to natural language generation (NLG), and hence to NL G itself, is a notoriously difficult problem, practically, theoretically and even methodologically. In this paper, we describe our recent experiences of implementing an NL G component of a larger question-answering system, and trying to understand and resolve some of these problems in this context. We examine the whole lifetime of an answer, from internal data structure to final expression as text, and look for characteristics of the processing which might help identify where NL G really begins. On the basis of this analysis we propose some principles to inform discussions on the scope of NL G as an individuated enterprise.

KW - Natural language generation

KW - NLG

M3 - Conference contribution with ISSN or ISBN

SP - 144

EP - 151

BT - Proceedings of the Second International Conference on Natural Language Generation

PB - Association for Computational Linguistics

ER -

Evans R, Piwek P, Cahill L. What is NLG? In Proceedings of the Second International Conference on Natural Language Generation. Association for Computational Linguistics. 2002. p. 144-151