Grammar Acquisition

Some of my early post-dissertation work explored computational models of first language acquisition, in particular the acquisition of syntax. The Amber model, which represented grammatical knowledge as production rules and relied on a discrimination mechanism for learning, matched a number of phenomena from the literature on child language.

My later work in this area was less psychologically oriented but continued to focus on general learning methods that could be used in domains other than language. The GRIDS system, which began as a rational reconstruction of Wolff's SNPR, uses a simplicity metric to guide search through a space of context-free grammars.

Related Publications

Langley, P., & Stromsten, S. (2000). Learning context-free grammars with a simplicity bias. Proceedings of the Eleventh European Conference on Machine Learning (pp. 220-228). Barcelona: Springer-Verlag.

Langley, P. (1991). Machine learning and language acquisition. Proceedings of the AAAI Spring Symposium on Machine Learning of Natural Language and Ontology. Stanford, CA: AAAI Press.

Langley, P., & Carbonell, J. G. (1987). Language acquisition and machine learning. In B. MacWhinney (Ed.), Mechanisms of language acquisition. Hillsdale, NJ: Lawrence Erlbaum.

Langley, P. (1987). Machine learning and grammar induction. Machine Learning, 2, 5-8.

Langley, P. (1982). Language acquisition through error recovery. Cognition and Brain Theory, 5, 211-255.

Langley, P. (1982). A model of early syntactic development. Proceedings of the 20th Annual Conference of the Society for Computational Linguistics (pp. 145-151). Toronto, Ontario.

Langley, P. (1980). A production system model of first language acquisition. Proceedings of the Eighth International Conference on Computational Linguistics (pp. 183-189). Tokyo, Japan.

For more information, send electronic mail to

© 1997-2018 Institute for the Study of Learning and Expertise. All rights reserved.