A Program That Acquires Language Using Positive and Negative Feedback

Authors

  • James Brand

DOI:

https://doi.org/10.1558/cj.v5i1.15-31

Keywords:

Acquire, superstate, doublematch rule, before and after rule, informant, positive network, negative network

Abstract

"Acquire" is an artificial intelligence application that learns language directly from examples. Sentences are input and classified by an informant as either good or bad. A pair of transition networks is built, one from the "good" input and one from the "bad" input using a pattern matching algorithm which states that a word can be classified by what comes immediately before and after it in a sentence. A sentence is recognized when it is accepted by the "good" network and rejected by the "bad" network. "Acquire" attempts to deal with problems such as overgeneration that arise in similar language learning programs.

References

Anderson, J, 1975. Computer simulation of a language acquisition system: A first report. In R. Soso, ed., Information Processing and Cognition: The Loyola Symposium. Washington, Erlbaum.

Barr, Avron and Edward A. Feigenbaum. 1981. The Handbook of Artificial Intelligence, Vol. III. Heuristech Press, Stanford, California.

Brand, James B. 1986. A pattern matching approach to language acquisition using positive and negative sentence samples. Unpublished Masters thesis, Wright State University Department of Computer Science and Engineering, Dayton, Ohio.

Gold, E. 1967. Language identification in the limit. Information and Control, 16, 447-474.

Hamburger, H. and K. Wexler. 1975. A mathematical theory of learning transformational grammar. J. Math Psychol., 12, 137-177.

Harris, L.R. 1974. natural language acquisition by robot. Technical Report TR74-1, Dartmouth College, Department of Mathematics. October.

Hill, Jane C. 1983. A Computational model of Language Acquisition in the Two-yearold. Bloomington, Indiana. Indian. University Linguistics Club.

Katke, William. 1985. Learning Language Using a Pattern Recognition Approach. Th. AI Magazine. Spring, 1985, 64-75.

Kelley, K. 1967. Early syntactic acquisition. Report No. P-3719. Santa Monica, California. The Rand Corp.

Pinker, Steven. 1979. Formal models of language learning. Cognition, September 1979,217-283.

Selfridge, M. 1980. A process model of language acquisition. Research Report 172, Yale University, Department of Computer Science, January

Downloads

Published

2013-01-14

Issue

Section

Articles

How to Cite

Brand, J. (2013). A Program That Acquires Language Using Positive and Negative Feedback. CALICO Journal, 5(1), 15-31. https://doi.org/10.1558/cj.v5i1.15-31

Most read articles by the same author(s)

1 2 3 4 5 6 7 8 9 10 > >>