A discourse model for gist preservation

  • Lucia Helena Machado Rino
  • Donia Scott
Natural Language Processing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1159)


This paper describes an approach to gist preservation during automatic summarization whereby the source is a complex information structure which must be “pruned” and organized in such a way as to make it appropriate for textual expression. Based on a discourse model, we propose a process whereby gist is guaranteed at the deep level according to communicative and rhetorical settings. The main function of such a goal-driven summarization model is to map intentions onto coherence relations whilst still observing the semantic dependency indicated by the message source. The discourse model is thus based on an association of intentionality, coherence and semantics, which guides the production of summary message sources that highlight the central proposition of the discourse.


Automatic summarization discourse modeling text generation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Cawsey, A. Generating Explanatory Discourse. In R. Dale; C. Mellish and M. Zock (eds.), Current Research in Natural Language Generation, pp. 75–101. London, Academic Press, 1990.Google Scholar
  2. Grosz, B. and Sidner, C. Attention, Intentions, and the Structure of Discourse. Computational Linguistics, Vol. 12, No. 3, 1986.Google Scholar
  3. Hobbs, J.R. On the Coherence and Structure of Discourse. Technical Report CSLI-85-37, Center for the Study of Language and Information, Stanford University, 1985.Google Scholar
  4. Hoey, M. On the Surface of Discourse. George Allen & Unwin (Publishers) Ltd., 1983.Google Scholar
  5. Hovy, E. Automated Discourse Generation Using Discourse Structure Relations. Artificial Intelligence 63, pp. 341–385, 1993.Google Scholar
  6. Jordan, M.P. An Integrated Three-pronged Analysis. In W.C. Mann and S.A. Thompson (eds.), Discourse Description: Diverse Linguistic Analyses of a Fund-Raising Text. John Benjamins Publishing Co., 1992.Google Scholar
  7. Levelt, W.J.M. Speaking: From Intention to Articulation. The MIT Press. Cambridge. 1989.Google Scholar
  8. Mann, W.C. and Thompson, S.A. Rhetorical Structure Theory: A Theory of Text Organization. Technical Report ISI/RS-87-190, June 1987.Google Scholar
  9. Maybury, M.T. Communicative Acts for Explanation Generation. Int. Journal of Man-Machine Studies 37, pp. 135–172, 1992.Google Scholar
  10. McKeown, K.R. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge University Press, 1985.Google Scholar
  11. Moore, J.D. and Paris, C. Planning Text for Advisory Dialogues: Capturing Intentional and Rhetorical Information. Computational Linguistics, Vol. 19, No. 4, pp. 651–694, 1993.Google Scholar
  12. Robin, J. Revision-Based Generation of Natural Language Summaries Providing Historical Background: Corpus-Based Analysis, Design, Implementation and Evaluation. PhD. Thesis. Columbia University, December 1994.Google Scholar
  13. Rino, L.H.M. Modelagem de Discurso para o Tratamento da Concisão e Preservação da Idéia Central na Geração de Textos. PhD. Thesis, Universidade de São Paulo, Brasil. Abril 1996.Google Scholar
  14. Rino, L.H.M. and Scott, D. Content selection in summary generation. XI Simpósio Brasileiro de Inteligência Artificial Fortaleza, Brazil, October 1994.Google Scholar
  15. Scott, D.R. and Souza, C.S. Getting the Message Across in RST-Based Text Generation. In R. Dale; C. Mellish and M. Zock (eds.), Current Research in Natural Language Generation. London, Academic Press, pp. 47–73, 1990.Google Scholar
  16. Sparck Jones, K. Discourse Modelling for Automatic Summarising. Tech. Rep. No. 290. University of Cambridge, Feb 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Lucia Helena Machado Rino
    • 1
  • Donia Scott
    • 2
  1. 1.DC-UFSCarSão Carlos-SPBrazil
  2. 2.ITRI - University of BrightonBrightonUK

Personalised recommendations