Skip to main content
Log in

A Connectionist Study on the Interplay of Nouns and Pronouns in Personal Pronoun Acquisition

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Cascade-correlation learning is used to model pronoun acquisition in children. The cascade-correlation algorithm is a feed-forward neural network that builds its own topology from input and output units. Personal pronoun acquisition is an interesting non-linear problem in psychology. A mother will refer to her son as you and herself as me, but the son must infer for himself that when he speaks to his mother, she becomes you and he becomes me. Learning the shifting reference of these pronouns is a difficult task that most children master. We show that learning of two different noun-and-pronoun addressee patterns is consistent with naturalistic studies. We observe a surprising factor in pronoun reversal: increasing the amount of exposure to noun patterns can decrease or eliminate reversal errors in children.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. A possible concern is that placing the noun in the unstable 0 region of the sigmoid makes nouns artificially difficult to learn—a contradiction to the intuition that nouns should be much easier to learn than personal pronouns. However, it should be noted that we are simulating pronoun acquisition and not noun acquisition. Thus, the primary goal of noun use is to model confusing inputs with respect to pronoun acquisition. Nouns do not tell the learner which pronoun to use in a given setting and can be viewed as confusion. Since a noun is no more similar to me than to you, it is neutral, hence the 0.

  2. These patterns are a way to test the network’s learning thus far, and the feedback from the patterns provides more learning for the network, producing the reinforcement learning effect.

  3. Technically, in phase 2 of standard learning, both the 9:1 and 5:5 networks learn at the same rate. However, due to the significant increase in learning of phase 1 by the 5:5 networks, second-borns learn faster overall.

References

  1. Berthiaume VG, Onishi KH, Shultz TR. A computational developmental model of the implicit false belief task. In: Love BC, McRae K, Sloutsky VM, editors. Proceedings of the 30th Annual Conference of the Cognitive Science Society. Austin, TX: Cognitive Science Society; 2008. p. 825–30.

  2. Charnet R. Speech roles and the development of personal pronouns. J Child Language. 1980;7:509–28.

    Google Scholar 

  3. Chiat S. Context-specificity and generalization in the acquisition of pronomial distinction. J Child Language. 1981;8:75–91.

    CAS  Google Scholar 

  4. Clark EV. From gesture to word: on the natural history of deixis in language acquisition. In: Bruner J, Garton A, editors. Human growth and development; Wolfson College Lectures 1976. Oxford: Oxford University Press; 1978. p. 85–120.

  5. Dandurand F, Shultz TR. Modelling acquisition of a torque rule on the balance-scale task. In: Taatgen N, van Rijn H, editors. Proceedings of the 31st Annual Conference of the Cognitive Science Society. Austin, TX: Cognitive Science Society; 2009. p. 1541–6.

  6. Egri L, Shultz TR. A compositional neural-network solution to prime-number testing. In: Proceedings of the 28th Annual Conference of the Cognitive Science Society. Mahwah, NJ: Erlbaum; 2006. p. 1263–8.

  7. Ervin-Tripp S. An overview of theories of grammatical development. The ontogenesis of grammar: theoretical symposium. 1971.

  8. Fahlman SE, Lebiere C. The cascade-correlation learning architecture. In: Touretzky DS, editor. Advances in neural information processing systems 2. San Mateo, CA: Morgan Kaufmann; 1990. p. 524–32.

  9. Jamrozik A, Shultz TR. Learning the structure of a mathematical group. In: McNamara D, Trafton G, editors. Proceedings of the 29th Annual Conference of the Cognitive Science Society. Mahwah, NJ: Lawrence Erlbaum; 2007. p. 1115–20.

  10. Oshima-Takane Y. Children learn from speech not addressed to them: The case of personal pronouns. J Child Language. 1998;15:95–108.

    Article  CAS  Google Scholar 

  11. Oshima-Takane Y. Analysis of pronominal errors: a case study. J Child Language. 1992;19:111–31.

    Article  CAS  Google Scholar 

  12. Oshima-Takane Y, Derevensky JL. Do later—born children delay in early language development? Paper presented at the International Conference on Infant Studies, Montreal; 1990.

  13. Oshima-Takane Y, Oram J. Acquisition of personal pronouns: what do comprehension data tell us? Paper presented at the International Society for the Study of Behavioural Development, Minneaplis, MN; 1991.

  14. Oshima-Takane Y, Takane Y, Shultz TR. The learning of first and second person pronouns in English: network models and analysis. J Child Language. 1999;26:545–75.

    Article  CAS  Google Scholar 

  15. de Paulo BM, Bonvillian JD. The effect on language development of the special characteristics of speech addressed to children. J Psycholinguistics Res. 1978;7:189–211.

    Article  Google Scholar 

  16. Schiff-Meyers N. From pronoun reversals to correct pronoun usage: a case study of a normally developing child. J Speech Hearing Disorders. 1983;48:385–94.

    Google Scholar 

  17. Schlimm D, Shultz TR. Learning the structure of abstract groups. In: Taatgen N, van Rijn H, editors. Proceedings of the 31st Annual Conference of the Cognitive Science Society. Austin, TX: Cognitive Science Society; 2009. p. 2100–5.

  18. Shultz TR, Schmidt WC. A cascade-correlation model of balance scale phenomena. In: Proceedings of the 13th Annual Conference of the Cognitive Science Society. Hillsdale, NJ: Erlbaum; 1991. p. 635–40

  19. Shultz TR, Vogel A. A connectionist model of the development of transitivity. In: Proceedings of the 26th Annual Conference of the Cognitive Science Society. Mahwah, NJ: Erlbaum; 2004. p. 1243–8.

  20. Shultz TR, Buckingham D, Oshima-Takane Y. A connectionist model of the learning of personal pronouns in English. Computational learning theory and natural learning systems: intersections between theory and experiment. 1994. p. 347–62.

  21. Shultz TR, Buckingham D, Oshima-Takane Y. Modelling cognitive development on balance scale phenomena. Machine Learning. 1994;16:57–86.

    Google Scholar 

  22. Takane Y, Oshima-Takane Y, Shultz TR. Network analyses: the case of first and second person pronouns. In: Proceedings of the 1995 IEEE International Conference on Systems, Man and Cybernetics. 1995. p. 3594–9.

Download references

Acknowledgments

We are grateful to Thomas R. Shultz for providing LISP code for the cascade-correlation algorithm, a thorough introduction to the subject and comments of an earlier draft and to Victoria Ly and Vincent G. Berthiaume for helpful comments.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Artem Kaznatcheev.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kaznatcheev, A. A Connectionist Study on the Interplay of Nouns and Pronouns in Personal Pronoun Acquisition. Cogn Comput 2, 280–284 (2010). https://doi.org/10.1007/s12559-010-9050-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-010-9050-7

Keywords

Navigation