Hybrid Computational Model for Producing English Past Tense Verbs

  • Maitrei Kohli
  • George D. Magoulas
  • Michael Thomas
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)


In this work, we explore the use of artificial neural networks (ANN) as computational models for producing English past tense verbs by combining them with the genetic algorithms (GA). The principal focus was to model the population variability exhibited by children in learning the past tense. This variability stems from genetic and environmental origins.We simulated the effects of genetic influences via variations in the neuro computational parameters of the ANNs, and the effects of environmental influences via a filter applied to the training set, implementing variation in the information available to the child produced by, for example, differences in socio-economic status. In the model, GA served two main purposes - to create the population of artificial neural networks and to encode the neuro computational parameters of the ANN into the genome. English past tense provides an interesting training domain in that it comprises a set of quasi-regular mappings. English verbs are of two types, regular verbs and irregular verbs. However, a similarity gradient also exists between these two classes. We consider the performance of the combination of ANN and GA under a range of metrics. Our tests produced encouraging results as to the utility of this method, and a foundation for future work in using a computational framework to capture population-level variability.


Feed forward neural networks imbalanced datasets hamming distance nearest neighbour genetic algorithms English past tense verbs quasi regular mappings 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Thomas, M.S.C., McClelland, J.L.: Connectionist models of cognition. In: Sun, R. (ed.) Cambridge Handbook of Computational Cognitive Modelling, pp. 23–58. Cambridge University Press, Cambridge (2008)CrossRefGoogle Scholar
  2. 2.
    Thomas, M.S.C., Karmiloff-Smith, A.: Connectionist models of development, developmental disorders and individual differences. In: Sternberg, R.J., Lautrey, J., Lubart, T. (eds.) Models of Intelligence: International Perspectives, pp. 133–150. American Psychological Association (2003)Google Scholar
  3. 3.
    Thomas, M.S.C., Ronald, A., Forrester, N.A.: Modelling socio-economic status effects on language development (2012) (manuscript submitted for publication)Google Scholar
  4. 4.
    Plunkett, K., Marchman, V.: U-shaped learning and frequency effects in a multilayered perceptron: Implications for child language acquisition. Cognition 38 (1991)Google Scholar
  5. 5.
    Lupyan, G., McClelland, J.L.: Did, Made, Had, Said: Capturing quasi – regularity in exceptions. In: 25th Annual Meeting of the Cognitive Science Society (2003)Google Scholar
  6. 6.
    Karaminis, T., Thomas, M.S.C.: A cross-linguistic model of the acquisition of inflectional morphology in English and modern Greek. In: Proceedings of the 32nd Annual Meeting of the Cognitive Science Society, August 11-14 (2010)Google Scholar
  7. 7.
    Thomas, M.S.C., Ronald, A., Forrester, N.A.: Modelling the mechanisms underlying population variability across development: Simulating genetic and environmental effects on cognition. DNL Tech report 2009-1 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Maitrei Kohli
    • 1
  • George D. Magoulas
    • 1
  • Michael Thomas
    • 2
  1. 1.Department of Computer Science and Information SystemsBirkbeck College, University of LondonUK
  2. 2.Department of Psychological SciencesBirkbeck College, University of LondonUK

Personalised recommendations