Implementation architectures for natural language generation

C. Mellish, Roger Evans

Research output: Contribution to journalArticle

Abstract

Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.
Original languageEnglish
Pages (from-to)261-282
Number of pages22
JournalNatural Language Engineering
Volume10
Issue number3-4
DOIs
Publication statusPublished - Sep 2004

Fingerprint

Software architecture
Processing

Bibliographical note

© 1998 Cambridge University Press

Cite this

@article{cddabf5b54184baebb6f1c680a8bc36c,
title = "Implementation architectures for natural language generation",
abstract = "Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.",
author = "C. Mellish and Roger Evans",
note = "{\circledC} 1998 Cambridge University Press",
year = "2004",
month = "9",
doi = "10.1017/S1351324904003511",
language = "English",
volume = "10",
pages = "261--282",
journal = "Natural Language Engineering",
issn = "1351-3249",
number = "3-4",

}

Implementation architectures for natural language generation. / Mellish, C.; Evans, Roger.

In: Natural Language Engineering, Vol. 10, No. 3-4, 09.2004, p. 261-282.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Implementation architectures for natural language generation

AU - Mellish, C.

AU - Evans, Roger

N1 - © 1998 Cambridge University Press

PY - 2004/9

Y1 - 2004/9

N2 - Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.

AB - Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.

U2 - 10.1017/S1351324904003511

DO - 10.1017/S1351324904003511

M3 - Article

VL - 10

SP - 261

EP - 282

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

IS - 3-4

ER -