A Reference Architecture for Generation Systems

Christopher Stuart Mellish, D. Scott, L. Cahill, D. Paiva, R. Evans, M. Reape

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.
Original languageEnglish
Pages (from-to)1-34
Number of pages34
JournalNatural Language Engineering
Volume12
Issue number1
Publication statusPublished - 2006

Fingerprint

Data structures
Specifications
language
multimedia
Natural Language
Language Generation
evaluation
evidence

Cite this

Mellish, C. S., Scott, D., Cahill, L., Paiva, D., Evans, R., & Reape, M. (2006). A Reference Architecture for Generation Systems. Natural Language Engineering, 12(1), 1-34.

A Reference Architecture for Generation Systems. / Mellish, Christopher Stuart; Scott, D.; Cahill, L.; Paiva, D.; Evans, R.; Reape, M.

In: Natural Language Engineering, Vol. 12, No. 1, 2006, p. 1-34.

Research output: Contribution to journalArticle

Mellish, CS, Scott, D, Cahill, L, Paiva, D, Evans, R & Reape, M 2006, 'A Reference Architecture for Generation Systems', Natural Language Engineering, vol. 12, no. 1, pp. 1-34.
Mellish CS, Scott D, Cahill L, Paiva D, Evans R, Reape M. A Reference Architecture for Generation Systems. Natural Language Engineering. 2006;12(1):1-34.
Mellish, Christopher Stuart ; Scott, D. ; Cahill, L. ; Paiva, D. ; Evans, R. ; Reape, M. / A Reference Architecture for Generation Systems. In: Natural Language Engineering. 2006 ; Vol. 12, No. 1. pp. 1-34.
@article{605eeb2c284041d28d8ad991791325aa,
title = "A Reference Architecture for Generation Systems",
abstract = "We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.",
author = "Mellish, {Christopher Stuart} and D. Scott and L. Cahill and D. Paiva and R. Evans and M. Reape",
year = "2006",
language = "English",
volume = "12",
pages = "1--34",
journal = "Natural Language Engineering",
issn = "1351-3249",
publisher = "Cambridge University Press",
number = "1",

}

TY - JOUR

T1 - A Reference Architecture for Generation Systems

AU - Mellish, Christopher Stuart

AU - Scott, D.

AU - Cahill, L.

AU - Paiva, D.

AU - Evans, R.

AU - Reape, M.

PY - 2006

Y1 - 2006

N2 - We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

AB - We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

M3 - Article

VL - 12

SP - 1

EP - 34

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

IS - 1

ER -