Academia.eduAcademia.edu

Outline

Title
Abstract
Roles of Data
Conclusions and Further Work
References
All Topics
Psychology
Cognitive Science

Implementation architectures for natural language generation

Profile image of Roger EvansRoger Evans

2004, Natural Language Engineering

https://doi.org/10.1017/S1351324904003511
visibility

…

description

22 pages

link

1 file

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. 1 The Case for a Generic Software Architecture for NLG Most natural language generation (NLG) systems have some kind of modular structure. The individual modules may differ in complex ways, according to whether they are based on symbolic or statistical models, what particular linguistic theories they embrace and so on. Ideally, such modules could be reused in other NLG systems. This would avoid duplication of work, allow realistic research specialisation and allow empirical comparison of different approaches. Examples of ideas that might give rise to reusable modules include:

Related papers

Architectures for Natural Language Generation: Problems and Perspectives
Koenraad De Smedt, michael zock

1993

Current research in natural language generation is situated in a computational linguistics tradition that was founded several decades ago. We critically analyse some of the architectural assumptions underlying existing systems and point out some problems in the domains of text planning and lexicalization. Guided by the identification of major generation challenges viewed from the angles of knowledge-based systems and cognitive psychology, we sketch some new directions for future research.

View PDFchevron_right
Building natural language generation systems
Robert Dale

Natural Language Engineering, 1997

The book is about natural language generation (NLG), which is a sub®eld of arti®cial intelligence and computational linguistics that is concerned with building computer software systems that can produce meaningful texts in English or other human languages from some underlying non-linguistic representation of information. In the introduction, the ®eld of NLG is brie¯y characterized from research-and applicationoriented perspectives and illustrated by screen shots produced by several systems. Then, conditions for bene®cial uses of this technology are elaborated and contrasted with conditions where other techniques are more appropriate. Moreover, methods for determining the intended functionality of a system to be built are discussed. The main sections of the book are devoted to the prototypical architecture of application-oriented NLG systems and their major processing phases: document planning, microplanning and surface realization. Each of these three phases is illustrated by a number of detailed examples, demonstrating the successive re®nements of utterance speci®cations in the course of processing. In the ®nal section, embedding of the natural language processing technology is discussed featuring typography, combined uses with graphics and hypertext, as well as integration with speech. The methods are illustrated by a large number of examples Ð the book contains more than 120 ®gures on its 248 pages. At the end of each section, a number of useful references for further reading are related to the section topics. In the appendix, a table summarizing the 35 systems referred in the book is given.

View PDFchevron_right

References (43)

  1. Barrutieta, G., J. Abaitua and J. Diaz. (2002) Cascading XSL Filters for Content Selection in Multilingual Document Generation. Procs of the Second Workshop on NLP and XML, Taipei.
  2. Bateman, J. (1997) Enabling Technology for Multilingual Natural Language Generation: The KPML Development Environment. Natural Language Engineering, 3(1):15-55.
  3. Bayer, S., C. Doran and B. George. (2001) Dialogue Interaction with the DARPA Com- municator Infrastructure: The Development of Useful Software. Poster presentation, HLT 2001.
  4. Beale, S., S. Nirenburg, E. Viegas and L. Wanner. (1998) De-Constraining Text Gen- eration. Procs of the Ninth International Workshop on Natural Language Generation, Niagara-on-the-Lake.
  5. Brew, C., D. McKelvie, R. Tobin, H. Thompson and A. Mikheev. (2000) The XML Library LT XML version 1.2. Obtainable at http://www.ltg.ed.ac.uk/software/xml/xmldoc/xmldoc.html.
  6. Cahill, L. (1999) Lexicalisation in Applied NLG Systems. Technical Report ITRI-99-04, ITRI, University of Brighton. obtainable at http://www.itri.brighton.ac.uk/rags/.
  7. Cahill, L. and M. Reape. (1999) Component tasks in applied NLG sys- tems. Technical Report ITRI-99-05, ITRI, University of Brighton. obtainable at http://www.itri.brighton.ac.uk/rags/.
  8. Cahill, L., J. Carroll, R. Evans, D. Paiva, R. Power, D. Scott, and K. van Deemter. (2001) From RAGS to RICHES: exploiting the potential of a flexible generation architecture. Procs of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-01), pages 98-105, Toulouse, France.
  9. Cahill, L., R. Evans, C. Mellish, D. Paiva, M. Reape, and D. Scott. (2001) The RAGS Ref- erence Manual . Technical Report ITRI-01-08, ITRI, University of Brighton. Available at http://www.itri.brighton.ac.uk/rags.
  10. Carroll, J., A. Copestake, D. Flickinger and V. Poznanski. (1999) An efficient chart gen- erator for (semi-)lexicalist grammars. Procs of the 7th European Workshop on Natural Language Generation (EWNLG'99), pages 86-95, Toulouse.
  11. Cheng, H., M. Poesio, R. Henschel and C. Mellish. (2001) Corpus-based NP Modifier Gen- eration. Procs of the Second Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL-01), Pittsburgh.
  12. Cunningham, H., Y. Wilks, and R. Gaizauskas. (1996) GATE -a general architecture for text engineering. Procs of the 16th International Conference on Computational Linguistics (COLING'96), volume 2, pages 1057-1060, Copenhagen.
  13. Danlos, L. (1984) Conceptual and Linguistic Decisions in Generation. Procs of the 10th International Conference on Computational Linguistics (COLING'84), Stanford.
  14. De Smedt, K. (1994) Parallelism in Incremental Sentence Generation. In G. Adriaens and U. Hahn (Eds) Parallel Natural Language Processing, Ablex, pages 421-447.
  15. De Smedt, K., H. Horacek, and M. Zock. (1996) Architectures for Natural Language Generation: Problems and Perspectives. In G. Adorni and M. Zock, (Eds) Trends in Natural Language Generation, Springer Verlag, pages 17-46.
  16. Elhadad, M. and J. Robin. (1992) Controlling content realization with functional uni- fication grammars. In R. Dale, E. Hovy, D. Roesner and O. Stock (Eds) Aspects of Automated Natural Language Generation, Lecture Notes in Artificial Intelligence, 587. Springer-Verlag, pages 89-104.
  17. Evans R., P. Piwek and L. Cahill. (2002) What is NLG? In Procs of the Second In- ternational Conference on Natural Language Generation (INLG-02), New York, pages 144-151.
  18. Grishman, R. (1995) TIPSTER Phase II Architecture Design Document Version 1.52. Technical Report, Dept of Computer Science, New York University.
  19. Herzog, G., A. Ndiaye, S. Merten, H. Kirchmann, T. Becker and P. Poller. (2004) Large- Scale Software Integration for Spoken Language and Multimodal Dialog Systems. Nat- ural Language Engineering, this issue.
  20. Hirschman, L. and R. Gaizauskas. (2001) Natural Language Question Answering: the view from here. Natural Language Engineering, 7(4):275-300.
  21. Hobbs, J. (1993) The generic information extraction system. Procs of the fifth Message Understanding Conference (MUC-5), Morgan Kaufman.
  22. Ide, N. and L. Romary. (2004) International Standard for a Linguistic Annotation Frame- work. Natural Language Engineering, this issue.
  23. Langkilde, I. and K. Knight. (1998) Generation that Exploits Corpus-based Statistical Knowledge. Procs of the Conference of the Association for Computational Linguistics (COLING/ACL-98).
  24. Langkilde-Geary, I. (2002) An Empirical Verification of Coverage and Correctness for a General-Purpose Sentence Generator. Procs of the Second International Conference on Natural Language Generation (INLG-02), New York, pages 17-24.
  25. Laprun, C., J. Fiscus, J. Garafolo and S. Pajot. (2002) A Practical Introduction to ATLAS. Procs of the Third International Conference on Language Resources and Evaluation (LREC-02), Las Palmas. Mellish and Evans
  26. Lavoie, B. and O. Rambow. (1997) A fast and portable realiser for text generation. Procs of the Fifth Conference on Applied Natural Language Processing (ANLP-97), Washington, pages 265-268.
  27. McDonald, D. (1981) MUMBLE: A Flexible System for Language Production. Procs of the Seventh International Joint Conference on Artificial Intelligence (IJCAI-81), Vancouver, page 1062.
  28. Mellish, C., A. Knott, J. Oberlander and M. O'Donnell. (1998) Experiments using Stochas- tic Search for Text Planning. Procs of the Ninth International Workshop on Natural Language Generation (INLG-98), Niagara-on-the-Lake, pages 98-107.
  29. Mellish, C., R. Evans, L. Cahill, C. Doran, D. Paiva, M. Reape, D. Scott, and N. Tipper. (2000) A representation for complex and evolving data dependencies in generation. Procs of the Language Technology Joint Conference, ANLP-NAACL2000, Seattle.
  30. Mellish, C., D. Scott, L. Cahill, R. Evans, D. Paiva and M. Reape. (2004) A Reference Architecture for Generation Systems. Natural Language Engineering, this issue.
  31. Nirenburg, S., V. Lesser and E. Nyberg. (1989) Controlling a Language Generation Planner. Procs of the 11th International Joint Conference on Artificial Intelligence (IJCAI-89), Detroit, pages 1524-1530.
  32. O'Donnell, M., A. Knott, C. Mellish, and J. Oberlander. (2001) ILEX: The architecture of a dynamic hypertext generation system. Natural Language Engineering, 7:225-250.
  33. Power, R. (2000) Planning texts by constraint satisfaction. Procs of the 18th International Conference on Computational Linguistics (COLING-2000), Saabruecken, pages 642- 648.
  34. Radev, D., N. Kambhatla, Y. Ye, C. Wolf and Z. Wlodek. (1999) DSML: A Proposal for XML Standards for Messaging Between Components of a Natural Language Dialogue System. Procs of the AISB'99 Workshop on Reference Architectures and Data Standards for NLP, Edinburgh.
  35. Reiter, E. (1994) Has a consensus NL generation architecture appeared and is it psycholin- guistically plausible? Procs of the 8th International Workshop on Natural Language Generation (INLG-94), Kennebunkport, pages 163-170.
  36. Reiter, E. (2001) Pipelines and Size Constraints. Computational Linguistics 26:251-259.
  37. Robin, J. and K. McKeown. (1996) Empirically designing and evaluating a new revision- based model for summary generation. Artificial Intelligence, 85(1-2).
  38. Rubinoff, R. (1992) Integrating Text Planning and Linguistic Choice by Annotating Linguistic Structures. In R. Dale, E. Hovy, D. Roesner and O. Stock (Eds) Aspects of Automated Natural Language Generation, Springer Verlag, pages 45-56.
  39. Seki, Y. (2001) XML Transformation-based three-stage pipelined Natural Language Gen- eration System. Procs of the Sixth Natural Language Processing Pacific Rim Symposium (NLPRS 2001), Tokyo, pages 767-768.
  40. Text Encoding Initiative. See http://www.tei-c.org/.
  41. Wahlster, W. (2001) Robust Translation of Spontaneous Speech: A Multi-Engine Ap- proach. Procs of the Seventeenth International Joint Conference on Artificial Intelli- gence (IJCAI-2001), Seattle.
  42. Wanner, L. and E. Hovy. (1996) The HealthDoc Sentence Planner Procs of the Eighth International Natural Language Generation Workshop (INLG-96), Herstmonceux, pages 1-10.
  43. Wilcock, G. (2001) Pipelines, Templates and Transformations: XML for Natural Language Generation. Procs of the first NLP and XML Workshop, Tokyo, pages 1-8.

Related papers

doi: 10.1017/S1351324906004104 Printed in the United Kingdom A Reference Architecture for Natural Language Generation Systems∗
Mike Reape

2004

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. * This is a revised and updated version of the paper "A Reference Architecture for Generation Systems" which appeared (in error) in Natural Language Engineering 10(3/4) the Special Issue on Software Architectures for Language Engineering. This version should be cited in preference to the earlier one. 1 This survey drew on Reiter's original (Reiter 1994) formulation of the model. The later (Reiter and Dale 2000) formulation uses slightly different terminology, which we also use here, but for our purposes is otherwise not significantly different. 2 The systems surveyed were:

View PDFchevron_right
A reference architecture for natural language generation systems
Donia Scott

Natural Language …, 2006

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.

View PDFchevron_right
Towards a Reference Architecture for Natural Language Generation Systems
Lynne Cahill

1999

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.

View PDFchevron_right
Towards a Reference Architecture for Natural Language Generation Systems, The RAGS project
Donia Scott

1999

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.

View PDFchevron_right
Reinterpretation of an existing NLG system in a Generic Generation Architecture
Donia Scott

Proceedings of the …, 2000

The RAGS project aims to define a reference architecture for Natural Language Generation (NLG) systems. Currently the major part of this architecture consists of a set of datatype definitions for specifying the input and output formats for modules within NLG systems. In this paper we describe our efforts to reinterpret an existing NLG system in terms of these definitions. The system chosen was the Caption Generation System.

View PDFchevron_right

Related topics

  • Cognitive Science
  • Computer Science
  • Natural language engineering
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved