Skip to main content

A Self-Evaluating Architecture for Describing Data

  • Conference paper
  • First Online:
Text, Speech, and Dialogue (TSD 2022)

Abstract

This paper introduces Linguoplotter, a workspace-based architecture for generating short natural language descriptions. All processes within Linguoplotter are carried out by codelets, small pieces of code each responsible for making incremental changes to the program’s state, the idea of which is borrowed from Hofstadter et al. [6]. Codelets in Linguoplotter gradually transform a representation of temperatures on a map into a description which can be output. Many processes emerge in the program out of the actions of many codelets, including language generation, self-evaluation, and higher-level decisions such as when to stop a given process, and when to end all processing and publish a final text. The program outputs a piece of text along with a satisfaction score indicating how good the program judges the text to be. The iteration of the program described in this paper is capable of linguistically more diverse outputs than a previous version; human judges rate the outputs of this version more highly than those of the last; and there is some correlation between rankings by human judges and the program’s own satisfaction score. But, the program still publishes disappointingly short and simple texts (despite being capable of longer, more complete descriptions). This paper describes: the workings of the program; a recent evaluation of its performance; and possible improvements for a future iteration.

The authors were partially supported by the UK EPSRC under grants EP/R513106/1 (Wright) and EP/S033564/1 (Sodestream: Streamlining Social Decision Making for Improved Internet Standards).

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Source code is available at https://github.com/georgeawright/linguoplotter.

References

  1. Belz, A. and Kow, E.: Comparing rating scales and preference judgements in language evaluation. In: Proceedings of the 6th International Conference on Natural Language Generation, pp. 7–15 (2010)

    Google Scholar 

  2. Clark, H.H.: Using Language. Cambridge University Press (1996)

    Google Scholar 

  3. Falkenhainer, B., Forbus, K.D., Gentner, D.: The structure mapping engine: algorithm and examples. Artif. Intell. 41, 1–63 (1989)

    Article  Google Scholar 

  4. French, R.M: The Subtlety of Sameness: A Theory and Computer Model of Analogy-Making. MIT Press (1995)

    Google Scholar 

  5. Gatt, A., Krahmer, E.: Survey of the state of the art in natural language generation: core tasks, applications, and evaluation. J. Artif. Intell. Res. 61, 65–170 (2018)

    Article  MathSciNet  Google Scholar 

  6. Hofstadter, D.: FARG: Fluid Concepts and Creative Analogies. Basic Books (1995)

    Google Scholar 

  7. Leppänen, L., Munezero, M., Granroth-Wilding, M., Toivonen, H.: Data-driven news generation for automated Journalism. In: Proceedings of the 10th International Natural Language Generation Conference, pp. 188–197 (2017)

    Google Scholar 

  8. Mitchell, M.: Analogy-Making as Perception: A Computer Model. MIT Press (1993)

    Google Scholar 

  9. Pickering, M.J., Garrod, S.: An integrated theory of language production and comprehension. Behav. Brain Sci. 36, 329–392 (2013)

    Article  Google Scholar 

  10. Pérez y Pérez, R., Sharples, M.: Mexica: a computer model of a cognitive account of creative writing. J. Exp. Theor. Artif. Intell. 13(2), 119–139 (2001)

    Google Scholar 

  11. Reiter, E: An architecture for data-to-text systems. In: Proceedings of the Eleventh European Workshop on Natural Language Generation, pp. 97–104 (2007)

    Google Scholar 

  12. Sharples, M.: How We Write: Writing as Creative Design. Routledge (1998)

    Google Scholar 

  13. Turner, M.: The Literary Mind: The Origins of Thought and Language. Oxford University Press (1996)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to George A. Wright .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wright, G.A., Purver, M. (2022). A Self-Evaluating Architecture for Describing Data. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2022. Lecture Notes in Computer Science(), vol 13502. Springer, Cham. https://doi.org/10.1007/978-3-031-16270-1_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-16270-1_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-16269-5

  • Online ISBN: 978-3-031-16270-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics