A Constraint-Motivated Model of Lexical Acquisition

Abstract

A cognitive model for learning associations between words and objects is presented. We first list basic constraints to which the model must adhere. The constraints arise from two sources. First they stem from observed psychological phenomena including typicality effects, extension errors observed from children and belief-dependent behavior. Secondly they arise from our choice to integrate the model in a unified theory of cognition. In presenting the constraints to the model's construction, we motivate our design decisions while describing our algorithm that takes a symbolic, production-based approach. The model's adherence to the constraints is further supported by some empirical results.

Cite

Text

Miller and Laird. "A Constraint-Motivated Model of Lexical Acquisition." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50023-4

Markdown

[Miller and Laird. "A Constraint-Motivated Model of Lexical Acquisition." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/miller1991icml-constraint/) doi:10.1016/B978-1-55860-200-7.50023-4

BibTeX

@inproceedings{miller1991icml-constraint,
  title     = {{A Constraint-Motivated Model of Lexical Acquisition}},
  author    = {Miller, Craig S. and Laird, John E.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {95-99},
  doi       = {10.1016/B978-1-55860-200-7.50023-4},
  url       = {https://mlanthology.org/icml/1991/miller1991icml-constraint/}
}