Abstract
We are developing a theory of probabilistic language learning in the context of robotic instruction in elementary assembly actions. We describe the process of machine learning in terms of the various events that happen on a given trial, including the crucial association of words with internal representations of their meaning. Of central importance in learning is the generalization from utterances to grammatical forms. Our system derives a comprehension grammar for a superset of a natural language from pairs of verbal stimuli like Go to the screw! and corresponding internal representations of coerced actions. For the derivation of a grammar no knowledge of the language to be learned is assumed but only knowledge of an internal language.
We present grammars for English, Chinese, and German generated from a finite sample of about 500 commands that are roughly equivalent across the three languages. All of the three grammars, which are context-free in form, accept an infinite set of commands in the given language.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Anderson, J.R. (1977). Induction of augmented transition networks. Cognitive Science, 1, 125–157.
Anderson, J.R. (1981). A theory of language acquisition based on general learning principles. Proceedings of the Seventh International Joint Conference on Artificial Intelligence, 97–103.
Estes, W.K., & Suppes, P. (1959). Foundations of linear models. In R.R. Bush, & W.K. Estes (Eds.), Studies in mathematical learning theory. Stanford, CA: Stanford University Press.
Feldman, J.A., Lakoff, G., Stolcke, A., & Hollbach Weber, S. (1990). Miniature language acquisition: A touchstone for cognitive science. Berkeley CA: ICSI.
Langley, P., & Carbonell, J.G. (1987). Language acquisition and machine learning. In B. MacWhinney (Ed.), Mechanisms of language acquisition. Hillsdale NJ: Erlbaum.
Regier, T. (1992). A connectionist architecture for learning motion-based spatial semantics. (Submitted to the 1992 Meeting of the Cognitive Science Society).
Siskind, J.M. (1992). Naive physics, event perception, lexical semantics, and language acquisition. M.I.T. Ph.D. Dissertation.
Stolcke, A. (1990). Learning feature-based semantics with simple recurrent networks. ICSI TR-90-015.
Suppes, P. (1973). Congruence of meaning. Proceedings and Addresses of the American Philosophical Association, 46, 21–38.
Suppes, P. (1991). Language for humans and robots. Oxford: Blackwell.
Suppes, P., Liang, L., & Böttner, M. (1992). Complexity issues in robotic machine learning of natural language. In L. Lam, & V. Naroditsky (Eds.), Modeling complex phenomena. New York: Springer.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Suppes, P., Böttner, M. & Liang, L. Comprehension Grammars Generated from Machine Learning of Natural Languages. Machine Learning 19, 133–152 (1995). https://doi.org/10.1023/A:1022663208628
Issue Date:
DOI: https://doi.org/10.1023/A:1022663208628