A Reference Architecture for Natural Language Generation Systems

Mellish, Chris; Scott, Donia; Cahill, Lynn; Paiva, Daniel; Evans, Roger and Reape, Mike (2006). A Reference Architecture for Natural Language Generation Systems. Journal of Natural Language Engineering, 12(1), pp. 1–34.

Full text available as:

Preview

PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (289Kb)

URL:	http://mcs.open.ac.uk/ds5473/publications/rags-JNL...
DOI (Digital Object Identifier) Link:	http://dx.doi.org/doi:10.1017/S1351324906004104
Google Scholar:	Look up in Google Scholar

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.

Item Type:	Journal Article
ISSN:	1351-3249
Extra Information:	Copyright held by the Cambridge University Press.
Keywords:	natural language generation; computational linguistics; reference architecture; RAGS; NLG
Academic Unit/Department:	Mathematics, Computing and Technology > Computing
Interdisciplinary Research Centre:	Centre for Research in Computing (CRC)
Item ID:	2326
Depositing User:	Donia Scott
Date Deposited:	14 Nov 2006
Last Modified:	06 Dec 2010 12:27
URI:	http://oro.open.ac.uk/id/eprint/2326

Actions (login may be required)

	View Item
	Public: Report issue / request change

Policies | Disclaimer