What is NLG?

Roger Evans, P. Piwek, Lynne Cahill

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

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 → …

Bibliographical note

Creative Commons Attribution Share-Alike License

Keywords

  • Natural language generation
  • NLG

Fingerprint Dive into the research topics of 'What is NLG?'. Together they form a unique fingerprint.

  • 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. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.8896