This paper describes preliminary research on “lexical choice” in generation: the relationships between words and the representations employed by the speaker for reasoning and modeling the situation. We hold that the bulk of the variance that we see at the surface level in language has its origins very deep in the conceptual system. Consequently, most of the burden of lexical choice must be taken on by this internal representation, and not by the generator proper as is customary today.

This work is exploratory rather than comprehensive. It studies the design consequences of three examples of lexical choice, introducing the devices “lexical clusters” and “action chain” as part of the representational system that organizes the selection process. In the first example the choice follows directly from the speaker’s categorial judgements. The next describes how the very same information can receive two substantially different lexical realizations depending on the speaker’s attitude toward it. In the last a choice usually ascribed to the generator is reanalyzed as conceptual, leading to a simpler processing architecture. These studies lend support to the conclusion that the selection of key lexical items is the first step in generation, with the choice criteria taken almost exclusively from the conceptual model and intentional attitudes of the speaker.


Computational Linguistics Linguistic Resource Natural Language Generation Text Planning Lexical Selection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Appelt, Doug (1985) “Some Pragmatic Issues in the Planning of Definite and Indefinite Noun Phrases”, in Proceedings of the 23rd Annual Meeting of the Association of Computational LinguisticsJuly 8–12, Univ. of Chicago, 198203. Google Scholar
  2. Bateman, John A. (1988) `Aspects of clause politeness in Japanese: an extended inquiry semantics treatment’. Proceedings of the 26th International Conference on Computational LinguisticsBuffalo, New York, pp147–154. Google Scholar
  3. Cumming, Susanna (1986) “The Lexicon in Text Generation”, Workshop on Automating the Lexicon, Pisa, Italy; available at a Technical Report from Information Sciences Institute, Marina Del Rey, California.Google Scholar
  4. Danlos, Laurence (1984) “Conceptual and linguistic decisions in generation”, in Proceedings of COLING-84, Stanford University, July 2–6, 501–504.Google Scholar
  5. Goldman, Neal (1975) “Conceptual Generation”, in Schank (ed.) Conceptual Information Processing, Elsevier.Google Scholar
  6. Hovy, Eduard (1987) Generating Natural Language under Pragmatic Constraints, Ph.D. Dissertation, Yale University.Google Scholar
  7. Hovy, Eduard (1988) “Generating Language with a Phrasal Lexicon”, in Natural Language Generation SystemsMcDonald and Bolc (eds.), Springer Verlag, 1988,353–384. Google Scholar
  8. Jacobs, Paul (1988) “Phred: a Generator for Natural Language Interfaces”, in Natural Language Generation Systems, McDonald and Bolc (eds.), Springer Verlag, 1988, 312–354.Google Scholar
  9. Kempen, Gerard (1987) editor Natural Language Generation: Recent Advances in Artificial Intelligence Psychology and LinguisticsKluwer Academic Publishers, Dordrecht, The Netherlands. Google Scholar
  10. Kukich, Karen (1988) “Fluency in Natural Language Reports”, in Natural Language Generation SystemsMcDonald and Bolc (eds.), Springer Verlag, 1988, 280–312. Google Scholar
  11. Levelt, Willem J.M. and Herbert Schriffers (1987) “Stages of Lexical Access” in Natural Language Generation: Recent Advances in Artificial Intelligence Psychology and LinguisticsKluwer Academic Publishers, Kempen (ed.) 1987, 395–404. Google Scholar
  12. Marcus, Mitchell (1987) “Generation Systems Should Choose Their Words”, Proceedings of TINLAP-3, New Mexico State University, January 7–9, 211214.Google Scholar
  13. McDonald, David (1983) “Natural Language Generation as a Computational Problem: an introduction”, in Brady and Berwick (eds.) Computational Models of DiscourseMIT Press, 1983, pp. 209–266. Google Scholar
  14. McDonald, David, JoAnn Brooks, Beverly Woolf and Philip Werner, Transition Networks for Discourse Management, Technical Report #86–34, Dept. Computer and Information Science, UMass., April 1986.Google Scholar
  15. McDonald, David and Marie Meteer (1988) “From Water to Wine: generating natural language text from today’s application programs”, in Proceedings of the 2nd Conference on Applied Natural Language Processing (ACL), Austin, February 9–12, 41–48. Google Scholar
  16. McGuire, Rod (1980) “Political Primaries and Words of Pain”, manuscript, Dept. of Computer Science, Yale; see also section 6 in Lehnert et al. “Boris— An Experiment in In-Depth Understanding of Narratives”, Artificial Intelligence 20 (1983) 15–62.Google Scholar
  17. McKeown, Kathleen (1985) Text Generation,Cambridge University Press.Google Scholar
  18. Meteer, Marie (1988) “Defining a Vocabulary for Text Planning”, in Proceedings of the Workshop on Text Planning and RealizationAAAI-88, St Paul, Minnesota, August 25, 115–112. Google Scholar
  19. Meteer, Marie (1989) “The Spokesman Natural Language Generation System”, Technical Report 7090, Bolt, Beranek, and Newman Inc., Cambridge, MA.Google Scholar
  20. Meteer, Marie, David McDonald Scott Anderson, David Forster, Linda Gay, Alison Huettner and Penelope Sibun (1987) “Mumble-86: Design and Implementation”, TR #87–87 Dept. Computer & Information Science, UMass., September 1987, 174 pgs.Google Scholar
  21. Nirenburg, Sergei, Victor Lesser and Eric Nyberg (1989) “Controlling a Lan-guage Generation Planner”, in Proceedings of IJCAI-89Detroit, August 21–25. Google Scholar
  22. Nirenburg, Sergei and Irene Nirenburg (1988) “A Framework for Lexical Selection in Natural Language Generation”, in Proceedings of COLING-88Budapest, August 22–27, 471–475. Google Scholar
  23. Pustejovsky, James and Sergei Nirenburg (1987) “Lexical Selection in the Process of Language Generation” Proceedings of the 25th Annual Meeting of the Association for Computational LinguisticsStanford, July 6–9, 201–206. Google Scholar
  24. Pustejovsky, James and Sergei Nirenburg (1988) “Event Semantic Structure”, Technical Report, Brandeis University.Google Scholar
  25. Rosenberg, Steve (1978) “Understanding in Incomplete Worlds”, AIM #475, Artificial Intelligence Lab, MIT.Google Scholar
  26. Wilensky, Robert (1976) “Using Plans to Understand Natural Language”, in Proceedings of the annual meeting of the Association for Computing MachineryHouston. Google Scholar

Copyright information

© Springer Science+Business Media New York 1991

Authors and Affiliations

  • David D. McDonald

There are no affiliations available

Personalised recommendations