Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Lexicalization in natural language generation: A survey

Abstract

In natural language generation, a meaning representation of some kind is successively transformed into a sentence or a text. Naturally, a central subtask of this problem is the choice of words, orlexicalization. In this paper, we propose four major issues that determine how a generator tackles lexicalization, and survey the contributions that researchers have made to them. Open problems are identified, and a possible direction for future research is sketched.

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

References

  1. Appelt, D. (1985).Planning Natural Language Utterances. Cambridge University Press: Cambridge.

  2. Bateman, J., Kasper, R., Moore, J. & Whitney, R. (1990).A General Organization of Knowledge for Natural Language Processing: The PENMAN Upper Model. Technical Report, Information Sciences Institute, University of Southern California.

  3. Becker, J. (1975). The Phrasal Lexicon. In Schank, R. C. & Nash-Webber, B. N. (eds.)Theoretical Issues in Natural Language Processing (TINLAP), 70–73. Cambridge, MA.

  4. Brachman, R. & Schmolze, J. (1985). An Overview of the KL-ONE Knowledge Representation System.Cognitive Science 9: 171–216.

  5. Buchberger, E. & Horacek, H. (1988). VIE-GEN: A Generator for German Texts. In McDonald, D. D. & Bolc, L. (eds.)Natural Language Generation Systems, Chapter 5, 166–204. Springer: New York.

  6. Busemann, S. (1993). A Holistic View of Lexical Choice. In Horacek, H. & Zock, M. (eds.)New Concepts in Natural Language Generation. Pinter: London.

  7. Carter, R. (1987).Vocabulary: Applied Linguistic Perspectives. Allen & Unwin: London.

  8. Cumming, S. (1986).The Lexicon in Text Generation. Technical Report ISI/RR-86-168, USC/ISI.

  9. Dale, R. (1989). Cooking up Referring Expressions. In Proceedings ofThe 27th Annual Meeting of the Association for Computational Linguistics, Vancouver.

  10. Danlos, L. (1987).The Linguistic Basis of Text Generation. Cambridge University Press.

  11. DiMarco, C., Hirst, G. & Stede, M. (1993). The Semantic and Stylistic Differentiation of Synonyms and Near-Synonyms. InWorking Notes of the AAAI Spring Symposium on Building Lexicons for Machine Translation, Stanford University.

  12. Elhadad, M. & McKeown, K. R. (1990). Generating Connectives. In Proceedings ofThe 13th International Conference on Computational Linguistics (COLING-90), 97–101. Helsinki.

  13. Elhadad, M. (1991). Generating Adjectives to Express the Speaker's Argumentative Intent. In Proceedings ofThe Fifth National Conference on Artificial Intelligence (AAAI-91), 98–104.

  14. Evens, M. W. (1988).Relational Models of the Lexicon. Cambridge University Press: Cambridge.

  15. Goldman, N. M. (1975). Conceptual Generation. In Schank, R. C. (ed.)Conceptual Information Processing. North-Holland: Amsterdam.

  16. Granville, R. (1984). Controlling Lexical Substitution in Computer Text Generation. In Proceedings ofThe 10th International Conference on Computational Linguistics (COLING-84), 381–384, Stanford.

  17. Gross, M. (1986). Lexicon-grammar and the Syntactic Analysis of French. In Proceedings ofThe 11th International Conference on Computational Linguistics (COLING-86), 275–282. Bonn.

  18. Healey, A. (1968). English Idioms.Kivung 1(2): 71–108.

  19. Heid, U. & Raab, S. (1989). Collocations in Multilingual Generation. In Proceedings ofThe Fourth Conference of the European Chapter of the Association for Computational Linguistics, 130–136, Manchester.

  20. Horacek, H. (1987). Choice of Words in the Generation Process of a Natural Language Interface.Applied Artificial Intelligence 1(1): 117–132.

  21. Horacek, H. (1990). The Architecture of a Generation Component in a Complete Natural Language Dialogue System. In Dale, R., Mellish, C. & Zock, M. (eds.)Current Research in Natural Language Generation, Chapter 8, 193–228. Academic Press: London.

  22. Hovy, E. H. (1988a). Generating Language with a Phrasal Lexicon. In McDonald, D. D. & Bolc, L. (eds.)Natural Language Generation Systems, Chapter 10, 353–384. Springer: New York.

  23. Hovy, E. H. (1988b).Generating Natural Language Under Pragmatic Constraints. Lawrence Erlbaum: Hillsdale, NJ.

  24. Iordanskaja, L., Kittredge, R. & Polguère, A. (1991). Lexical Selection and Paraphrase in a Meaning-Text Generation Model. In Paris, C. L., Swartout, W. R. & Mann, W. C. (eds.)Natural Language Generation in Artificial Intelligence and Computational Linguistics, Chapter 11, 293–312. Kluwer: Dordrecht.

  25. Jacobs, P. S. (1985). PHRED: A Generator for Natural Language Interfaces.Computational Linguistics 11(4): 219–242.

  26. Jacobs, P. S. (1987). Knowledge-Intensive Natural Language Generation.Artificial Intelligence 33: 325–378.

  27. Kantrowitz, M. & Bates, J. (1992). Integrated Natural Language Generation Systems. In Dale, R., Hovy, E., Rösner, D. & Stock, O. (eds.)Aspects of Automated Natural Language Generation — Proceedings of the 6th International WS on Natural Language Generation. Springer: Berlin/Heidelberg.

  28. Kukich, K. (1983). Design and Implementation of a Knowledge-Based Report Generator. In Proceedings ofThe 21st Annual Meeting of the Association for Computational Linguistics, 145–150. Cambridge, MA.

  29. Kukich, K. (1987). Where Do Phrases Come From: Some Preliminary Experiments in Connectionist Phrase Generation. In Kempen, G. (ed.)Natural Language Generation: New Results in Artificial Intelligence, Psychology and Linguistics, Chapter 26, 405–421. Martinus Nijhoff: Dordrecht.

  30. Kukich, K. (1988). Fluency in Natural Language Reports. In McDonald, D. D. & Bolc, L. (eds.)Natural Language Generation Systems, Chapter 8, 280–311. Springer: New York.

  31. Marcus, M. (1987). Generation Systems Should Choose Their Words. In Wilks, Y. (ed.)Theoretical Issues in Natural Language Processing, 211–214. New Mexico State University: Las Cruces.

  32. Matthiessen, C. (1991). Lexico(Grammatical) Choice in Text Generation. In Paris, C. L., Swartout, W. R. & Mann, W. C. (eds.)Natural Language Generation in Artificial Intelligence and Computational Linguistics, Chapter 10, 249–292. Kluwer: Dordrecht.

  33. McDonald, D. D. (1991). On the Place of Words in the Generation Process. In Paris, C. L., Swartout, W. R. & Mann, W. C. (eds.)Natural Language Generation in Artificial Intelligence and Computational Linguistics, 227–248. Kluwer: Dordrecht.

  34. McKeown, K. & Robin, J. (1993). Tailoring Lexical Choice to the User's Vocabulary in Multimedia Explanation Generation. In Proceedings ofThe 31st Annual Meeting of the Association for Computational Linguistics, 226–234, Columbus.

  35. McKeown, K., Elhadad, M., Fukumoto, Y., Lim, J., Lombardi, C., Robin, J. & Smadja, F. (1990). Natural Language Generation in COMET. In Dale, R., Mellish, C. & Zock, M. (eds.)Current Research in Natural Language Generation, Chapter 5, 103–139. Academic Press: London.

  36. Mel'čuk, I. A. & Polguère, A. (1987). A Formal Lexicon in the Meaning-Text Theory (or How to Do Lexica with Words).Computational Linguistics 13(3–4): 261–275.

  37. Miezitis, M. A. (1988). Generating Lexical Options by Matching in a Knowledge Base. Technical Report CSRI-217, University of Toronto.

  38. Nirenburg, S. & Nirenburg, I. (1988). A Framework for Lexical Selection in Natural Language Generation. In Proceedings ofThe 12th International Conference on Computational Linguistics (COLING-88), 471–475, Budapest.

  39. Nogier, J. & Zock, M. (1992). Lexical Choice as Pattern Matching. In Nagle, T. E., Nagle, J. A., Gerholz, L. L. & Eklund, P. W. (eds.)Conceptual Structures: Current Research and Practice. Ellis Horwood: New York.

  40. Novak, H.-J. (1988). Generating Referring Phrases in a Dynamic Environment. In Zock, M. & Sabah, G. (eds.)Advances in Natural Language Generation Vol. 2, 70–73. Pinter: London.

  41. Novak, H.-J. (1993). Ontology and Lexical Choice. In Horacek, H. & Zock, M. (eds.)New Concepts in Natural Language Generation. Pinter: London.

  42. Penman-Group, (1989).The Penman Documentation: the Primer, the User Guide, the Reference Manual, the NIGEL Manual. Technical Report, Information Sciences Institute, University of Southern California.

  43. Pustejovsky, J. & Nirenburg, S. (1987). Lexical Selection in the Process of Language Generation. In Proceedings ofThe 25th Annual Meeting of the Association for Computational Linguistics, 201–206.

  44. Reiter, E. B. (1990). A New Model for Lexical Choice for Open-Class Words. In Proceedings ofThe Fifth International Natural Language Generation Workshop, 23–30. Dawson, PA.

  45. Robin, J. (1990).Lexical Choice in Natural Language Generation. Technical Report CUCS-04090, Columbia University, New York.

  46. Rosch, E. (1978). Principles of Categorization. In Rosch, E. & Lloyd, B. (eds.)Cognition and Categorization. Lawrence Erlbaum: Hillsdale, NJ.

  47. Schank, R. C. (1975).Conceptual Information Processing. Elsevier-North Holland: New York.

  48. Smadja, F. & McKeown, K. R. (1991). Using Collocations for Language Generation.Computational Intelligence 7: 229–239.

  49. Sondheimer, N., Cumming, S. & Albano, R. (1990). How to Realize a Concept: Lexical Selection and the Conceptual Network in Text Generation.Machine Translation 5(1): 57–78.

  50. Sowa, J. F. (1984).Conceptual Structures: Information Processing in Mind and Machine. Addison Wesley: New York.

  51. Stede, M. (1993a). Lexical Choice Criteria in Language Generation. In Proceedings ofThe Sixth Conference of the European Chapter of the Association for Computational Linguistics, Utrecht.

  52. Stede, M. (1993b). Lexical Options in Multilingual Generation from a Knowledge Base. InWorking notes of the Fifth European Workshop on Natural Language Generation, Pisa.

  53. Van Noord, G. (1990). An Overview of Head-driven Bottom-up Generation. In Dale, R., Mellish, C. & Zock, M. (eds.)Current Research in Natural Language Generation, Chapter 6, 141–166. Academic Press: London.

  54. Wanner, L. & Bateman, J. A. (1990). A Collocational Based Approach to Salience-Sensitive Lexical Selection. In Proceedings ofThe Fifth International Natural Language Generation Workshop, 31–38, Dawson, PA.

  55. Ward, N. (1990). Issues in Word Choice. In Proceedings ofThe 13th International Conference on Computational Linguistics (COLING-90), 726–731, Helsinki.

  56. Ward, N. (1991).A Flexible, Parallel Model of Natural Language Generation. Technical Report UCB/CSD-91/629, UC Berkeley, Computer Science Division.

Download references

Author information

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Stede, M. Lexicalization in natural language generation: A survey. Artif Intell Rev 8, 309–336 (1994). https://doi.org/10.1007/BF00849062

Download citation

Key words

  • natural language generation
  • lexical choice