Skip to main content

TECHDOC: A System for the Automatic Production of Multilingual Technical Documents

  • Conference paper
Konvens 92

Part of the book series: Informatik aktuell ((INFORMAT))

Abstract

The availability of technical documents in multiple languages is a problem of increasing significance, particularly in Europe. We propose to exploit natural language generation technology to help overcome the documentation problem. We focused on multilingual automobile manuals, specifically maintenance instructions, and analyzed them in terms of underlying technical knowledge and text structure. These investigations led us to a design of a system for the automatic, multilingual generation of such maintenance manuals. TECHDOC uses a domain knowledge base to first construct a language-independent text representation, which is then transformed into a collection of individual sentence plans. These are given to language-specific sentence generators to produce the desired text.

Zusammenfassung

Die Verfügbarkeit technischer Dokumente in mehreren Sprachen wird besonders in Europa immer bedeutsamer. Um das Dokumentationsproblem zu lösen, schlagen wir vor, die Möglichkeiten der automatischen Sprachgenerierung auszuschöpfen. Wir haben mehrsprachige Automobilhandbücher, speziell Wartungsinformationen, auf das zugrundeliegende technische Wissen sowie auf Textstrukturen hin untersucht. Daraus entstand das Design eines Systems zur automatischen, mehrsprachigen Generierung solcher Handbücher. TECHDOC erstellt aus einer Wissensbasis mit Gebietswissen zunächst eine sprachunabhängige Textrepräsentation, die dann in eine Folge von Satzplänen transformiert wird. Diese werden schließlich sprachspezifischen Satzgeneratoren zur Textproduktion übergeben.

Part of the work reported in this paper has been carried out during an internship at FAW Ulm funded from the ICSI exchange program. Thereafter, the work has been supported by a University of Toronto Open Doctoral Fellowship.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 49.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 59.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. S. Feiner, K.R. McKeown. Coordinating text and graphics in explanation generation. In: CAIA 90: Proceedings of the IEEE conference on AI applications, IEEE, 1990.

    Google Scholar 

  2. H. Horacek. An Integrated View of Text Planning. In: Dale, Hovy, Rösner, Stock (Eds.): Aspects of Automated Natural Language Generation. Springer, Berlin/Heidelberg 1992.

    Google Scholar 

  3. E. H. Hovy. Unresolved Issues in Paragraph Planning. In: Dale, Mellish, Zock (Eds.): Current Research in NLG. Academic Press, New York 1990.

    Google Scholar 

  4. J. Levine, A. Cawsey, C. Mellish, L. Poynter, E. Reiter, P. Tyson and J. Walker. IDAS: Combining hypertext and natural language generation. In: Proceedings of the Third European Workshop on Natural Language Generation, pages 55–62. Innsbruck, Austria 1991.

    Google Scholar 

  5. R. M. MacGregor and R. Bates. The Loom Knowledge Repre-sentation Language. USC/Information Science Inst. Tech. Rep. ISI/RS-87-188.

    Google Scholar 

  6. W. Mann and S. Thompson. Rhetorical structure theory: Toward a functional theory of text Organization. Text, 8, 243–281.

    Google Scholar 

  7. J. D. Moore and C. L. Paris. Planning Text for Advisory Dialogues. In: Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics, pages 203–211. 1989.

    Chapter  Google Scholar 

  8. The Penman Documentation. Unpublished documentation for the Penman language generation system. USC/Information Science Institute.

    Google Scholar 

  9. D. Rösner. The Generation System of the SEMSYN Project: Towards a Task-Independent Generator for German. In: Zock, Sabah (Eds.): Advances in Natural Language Generation: An Interdisciplinary Perspective. Pinter Publishers, London 1988.

    Google Scholar 

  10. D. Rösner, M. Stede. Customizing RST for the Automatic Production of Technical Manuals. In: Dale, Hovy, Rösner, Stock (Eds.): Aspects of Automated Natural Language Generation. Springer, Berlin/Heidelberg 1992.

    Google Scholar 

  11. K. Vander Linden, S. Cumming, and J. Martin. Using System Networks to Build Rhetorical Structures. In: Dale, Hovy, Rösner, Stock (Eds.): Aspects of Automated NLG. Springer, Berlin/Heidelberg 1992.

    Google Scholar 

  12. W. Wahlster, E. André, W. Graf, T. Rist. Designing Illustrated Texts: How Language Production is inßuenced by Graphics Generation. Fifth Conference of the European Chapter of the ACL. Berlin 1991.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1992 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Rösner, D., Stede, M. (1992). TECHDOC: A System for the Automatic Production of Multilingual Technical Documents. In: Görz, G. (eds) Konvens 92. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77809-4_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-77809-4_34

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-55959-7

  • Online ISBN: 978-3-642-77809-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics