Abstract
It is difficult to estimate the probability of a word’s context because of sparse data problems. If appropriate care is taken, we find that it is possible to make useful estimates of contextual probabilities that improve performance in a spelling correction application. In contrast, less careful estimates are found to be useless. Specifically, we will show that the Good-Turing method makes the use of contextual information practical for a spelling corrector, while attempts to use the maximum likelihood estimator (MLE) or expected likelihood estimator (ELE) fail. Spelling correction was selected as an application domain because it is analogous to many important recognition applications based on a noisy channel model (such as speech recognition), though somewhat simpler and therefore possibly more amenable to detailed statistical analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Box, G. E. P., and G. C. Tiao, 1973 Bayesian Inference in Statistical Analysis, Addison-Wesley, Reading, Massachusetts.
Brown, P., J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, R. Mercer, and P. Pietra, 1988, “A Statistical Approach to French/English Translation,” Proceedings RIA088, Conference on User-oriented Content-based Text and Image Handling, Cambridge, Mass, March 21–24.
Chomsky, N., “Three Models for the Description of Language,” IRE Transactions on Information Theory, vol. IT-2, Proceedings of the Symposium on Information Theory, 1956.
Church, K. W. and W. A. Gale, 1990, “Enhanced Good-Turing and Cat-Cal: Two New Methods for Estimating Probabilities of English Bigrams,” submiued to Computer, Speech, and Language, Academic Press.
Gale, W. A. and K. W. Church, 1990, “What’s Wrong with Adding One?” submitted to IEEE Transactions on Acoustics, Speech, and Signal Processing.
Good, I. J., 1953, “The population frequencies of species and the estimation of population parameters,” Biometrika, v. 40, pp. 237–264.
Kernighan. M. D., K. W. Church, W. A. Gale, 1989, “A Spelling Corrector Based on Error Frequencies” Proceedings of the Thirteenth International Conference on Computational Linguistics
Nadas, A., (1984), “Estimation of probabilities in the language model of the IBM speech recognition system,” IEEE Transactions on Acoustics, Speech, and Signal Processing, v. ASSP-32 pp. 859–861.
Steinhaus, H., (1957), “The problem of estimation,” Annals of Mathematical Statistics, v. 28, pp. 633–648.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Physica-Verlag Heidelberg
About this paper
Cite this paper
Gale, W.A., Church, K.W. (1990). Estimation Procedures for Language Context: Poor Estimates are Worse than None. In: Momirović, K., Mildner, V. (eds) Compstat. Physica-Verlag HD. https://doi.org/10.1007/978-3-642-50096-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-50096-1_11
Publisher Name: Physica-Verlag HD
Print ISBN: 978-3-7908-0475-1
Online ISBN: 978-3-642-50096-1
eBook Packages: Springer Book Archive