Computational investigation of early child language acquisition using multimodal neural networks: a review of three models

  • Authors:
  • Abel Nyamapfene

  • Affiliations:
  • School of Engineering, Computing and Mathematics, University of Exeter, Exeter, UK

  • Venue:
  • Artificial Intelligence Review
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Current opinion suggests that language is a cognitive process in which different modalities such as perceptual entities, communicative intentions and speech are inextricably linked. As such, the process of child language acquisition is one in which the child learns to decipher this inextricability and to acquire language capabilities starting from gesturing, followed by language dominated by single word utterances, through to full-blown native language capability. In this paper I review three multimodal neural network models of early child language acquisition. Using these models, I show how computational modelling, in conjunction with the availability of empirical data, can contribute towards our understanding of child language acquisition. I conclude this paper by proposing a control theoretic approach towards modelling child language acquisition using neural networks.