Advertisement

Using the conceptual graphs operations for natural language generation in medicine

  • J. C. Wagner
  • R. H. Baud
  • J. -R. Scherrer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 954)

Abstract

Natural language generation systems for the medical domain have to take into account the specific domain vocabulary as well as the particular language style of a highly conventionalised language. This is particularily relevant for multilingual generation.

We have developed a system for multilingual natural language generation in medicine, based on the Conceptual Graphs formalism and using a semantic model of medicine. The latter is being developed as part of the European project GALEN and it intends to be a language-independent, semantically valid model of clinical terminology.

Within the system we make intensive use of the operations defined in the Conceptual Graphs formalism in order to deal with the specific requirements of the medical language, multilinguality and the specific modelling style encountered within the GALEN-model. The approach has been applied to several languages, with a main focus on English and French. It has also been used within a clinical demonstrator application.

Keywords

Natural Language Generation multilingual systems lexical choice medical information systems domain terminology 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Musen MA. Dimensions of Knowledge Sharing and Reuse. Comput Biomed Research 1992; 25:435–467.Google Scholar
  2. [2]
    Rector AL, Nowlan WA, Kay S. Conceptual Knowledge: The core of medical information systems. In: Lun KC et al. (eds). MEDINFO 92. Proceedings. Amsterdam: North-Holland, 1992:1420–1426.Google Scholar
  3. [3]
    Evans DA, Cimono JJ, Hersh WR et al. Toward a Medical-concept Representation Language. J Am Med Informatics Assoc 1994; 1:207–217.Google Scholar
  4. [4]
    Ceusters W, Deville G, Buekens F. The Chimera of Purpose-and Language Independent Concept Systems in Health Care. In: Barahona P, Veloso M, Bryant J (eds). MIE 94. Proceedings. 1994: 208–212.Google Scholar
  5. [5]
    Campbell KE, Wieckert K, Fagan LM, Musen MA. A Computer-based Tool for Generation of Progress Notes. In: Safran C (ed). SCAMC 93. Proceedings. New York: McGraw-Hill, 1993: 284–288.Google Scholar
  6. [6]
    Bernauer J, Gumrich K, Kutz S et al. An Interactive Report Generator for Bone Scan Studies. In: Clayton PD (ed). SCAMC 91. Proceedings. New York: McGraw-Hill, 1991: 858–860.Google Scholar
  7. [7]
    Kuhn K, Zemmler T, Reichert M, Heinlein C, Roesner D. Structured Data Collection and Knowledge-Based User Guidance for Abdominal Ultrasound Reporting. In: Safran C (ed). SCAMC 93. Proceedings. New York: McGraw-Hill, 1993: 311–315.Google Scholar
  8. [8]
    Lindberg DAB, Humphreys BL, McCray AT. The Unified Medical Language System. Meth Inform Med 1993; 32: 281–291.Google Scholar
  9. [9]
    Rothwell DJ, Cote RA, Cordeau JP, Boisvert MA. Developing a Standard Data Structure for Medical Language — The SNOMED Proposal. In: Safran C (ed). SCAMC 93. Proceedings. New York: McGraw-Hill, 1993:695–699.Google Scholar
  10. [10]
    Rector AL, Solomon WD, Nowlan WA, Rush TW, Zanstra PE, Claassen WMA. A Terminology Server for Medical Language and Medical Information Systems. Meth Inform Med 1995; 34:147–57.Google Scholar
  11. [11]
    Rector AL, Nowlan WA, Glowinsky A. Goals for Concept Representation in the GALEN project. In: Safran C (ed). SCAMC 93. New York: McGraw-Hill, 1993:414–418.Google Scholar
  12. [12]
    Sowa JF. Conceptual Structures: Information Processing in Mind and Machine. Reading, MA: Addison-Wesley Publishing Company, 1984.Google Scholar
  13. [13]
    Wagner JC, Solomon WD, Michel P-A, Juge C, Baud RH, Rector AL, Scherrer J-R. Multilingual Natural Language Generation as Part of a Medical Terminology Server. To be published in: Greenes RA, Peterson H, Protti D (eds). MEDINFO 95. Proceedings of the 8th World Congress on Medical Informatics, Vancouver, Canada, July 23–27,1995.Google Scholar
  14. [14]
    Baud RH, Rassinoux A-M, Scherrer J-R. Natural Language Processing and Semantical Representation of Medical Texts. Meth Inform Med 1992; 31: 117–125.Google Scholar
  15. [15]
    Baud RH, Rassinoux A-M, Wagner JC et al. Representing Clinical Narratives using Conceptual Graphs. Meth Inform Med 1995; 34:176–86.Google Scholar
  16. [16]
    Rassinoux A-M, Baud RH, Scherrer J-R. A Multilingual Analyser of Medical Texts. In: Tepfenhart WM, Dick JP, Sowa JF (eds). Conceptual Structures: Current Practices. Second International Conference on Conceptual Structures, ICCS'94. Berlin: Springer-Verlag, 1994: 84–96.Google Scholar
  17. [17]
    Wagner JC, Rassinoux A-M, Baud RH, Scherrer J-R. Generating Noun Phrases from a Medical Knowledge Representation. In: Barahona P, Veloso M, Bryant J (eds). MIE 94. Proceedings. 1994: 218–223.Google Scholar
  18. [18]
    Nogier J-F, Zock M. Lexical Choice as Pattern Matching. In: Nagle T, Nagle J, Gerholz L, Eklund P (eds). Current Directions in Conceptual Structures Research. Reading, MA: Addison-Wesley, 1991.Google Scholar
  19. [19]
    Nogier J-F. Génération automatique de langage et graphes conceptuels. Paris: Hermès, 1991.Google Scholar
  20. [20]
    Alpay LL, Lovis C, Nowlan WA et al. Constructing Clinical Applications: The Galen Approach. To be published in: Greenes RA, Peterson H, Protti D (eds). MEDINFO 95. Proceedings of the 8th World Congress on Medical Informatics, Vancouver, Canada, July 23–27,1995.Google Scholar
  21. [21]
    Baud R, Lovis C, Rassinoux A-M et al. Towards a Medical Linguistic Knowledge Base. To be published in: Greenes RA, Peterson H, Protti D (eds). MEDINFO 95. Proceedings of the 8th World Congress on Medical Informatics, Vancouver, Canada, July 23–27,1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • J. C. Wagner
    • 1
  • R. H. Baud
    • 1
  • J. -R. Scherrer
    • 1
  1. 1.Medical Informatics CentreGeneva University HospitalGenevaSwitzerland

Personalised recommendations