Skip to main content

Finetuning NLG Through Experiments with Human Subjects: The Case of Vague Descriptions

  • Conference paper
Natural Language Generation (INLG 2004)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3123))

Included in the following conference series:

Abstract

This discussion paper describes a sequence of experiments with human subjects aimed at finding out how an nlg system should choose between the different forms of a gradable adjective. This case study highlights some general questions that one faces when trying to base nlg systems on empirical evidence: one question is what task to set a subject so as to obtain the most useful information about that subject, another question has to do with differences between subjects.

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

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bierwisch, M.: The semantics of gradation. In: Bierwisch, M., Lang, E. (eds.) Dimensional Adjectives, pp. 71–261. Springer, Berlin (1989)

    Google Scholar 

  2. Jordan, P.W.: Can Nominal Expressions Achieve Multiple Goals?: An Empirical Study. In: Procs. of ACL 2000, Hong Kong (2000)

    Google Scholar 

  3. Kamp, H.: Two theories about adjectives. In: Keenan, E. (ed.) Semantics for natural language, Cambridge University Press, Cambridge (1975)

    Google Scholar 

  4. Klein, E.: A semantics for positive and comparative adjectives. Linguistics and Philosophy 4 (1980)

    Google Scholar 

  5. Oberlander, J.: Do the right thing. but expect the unexpected. Computational Linguistics 24(3), 501–507 (1998)

    Google Scholar 

  6. Pechmann, T.: Incremental Speech Production and Referential Overspecification. Linguistics 27, 98–110 (1989)

    Article  Google Scholar 

  7. Piwek, P., Cremers, A.: Dutch and English Demonstratives: A Comparison. Language Sciences 18(3-4), 835–851 (1996)

    Article  Google Scholar 

  8. Reiter, E., Sripada, S.: Should Corpora Texts Be Gold Standards for NLG? In: Proceedings of INLG 2002, pp. 97–104 (2002)

    Google Scholar 

  9. Stevenson, R.J., Crawley, R.A., Kleinman, D.: Thematic roles, focus and the representation of events. Language and Cognitive Processes 9, 519–548 (1994)

    Article  Google Scholar 

  10. Synthese. Special issue of the journal Synthese on semantic vagueness. Synthese 30 (1975)

    Google Scholar 

  11. Turing, A.: Computing Machinery and Intelligence. Mind 59(236), 433–460 (1950)

    Article  MathSciNet  Google Scholar 

  12. van Deemter, K.: Generating Vague Descriptions. In: Procs. of Int. Conf. on Natural Language Generation (INLG 2000), Mitzpe Ramon (2000)

    Google Scholar 

  13. van Deemter, K.: Computational Generation of Vague Descriptions. ITRI, University of Brighton (manuscript)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

van Deemter, K. (2004). Finetuning NLG Through Experiments with Human Subjects: The Case of Vague Descriptions. In: Belz, A., Evans, R., Piwek, P. (eds) Natural Language Generation. INLG 2004. Lecture Notes in Computer Science(), vol 3123. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27823-8_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-27823-8_4

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-22340-5

  • Online ISBN: 978-3-540-27823-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics