Abstract
This paper contains an outline of two attempts at the development of language modeling methods superior to the usual trigram approach. We will present no proofs, and instead treat the topic from a completely heuristic point of view. These methods were developed by members of the IBM Continuous Speech Recognition Group, mainly by L.R. Bahl, RF. Brown, S.A. Della Pietra, V.J. Della Pietra, P.V. deSouza, R.L. Mercer, and S. Roukos.
This is a preview of subscription content, log in via an institution to check access.
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
L.R. Bahl, P.F. Brown, RV. de Souza, and R.L. Mercer: “A tree-based language model for natural language speech recognition”, IEEE Transactions on Acoustics, Speech and Signal Processing, 37: pp. 1001–1008, July 1989.
RF. Brown, S.A. Della Pietra, VJ. Della Pietra, R.L. Mercer, and P.S. Resnik: “Language modeling using decision trees”, an IBM Research Report, 1991.
P.F. Brown, VJ. Della Pietra, P.V. deSouza, J.C. Lai, and R.L. Mercer: “Class-based ngram models of natural language”, Computational Linguistics, Vol. 18, No.4, pp. 467–480, December 1992.
S. Kullback: Information Theory and Statistics, Wiley, New York1959
J.N. Darroch and D. Ratcliff: “Generalized iterative scaling for log-linear models”, The Annals of Mathematical Statistics, Vol 43, pp. 1470–1480, 1972.
I. Csiszar and G. Longo: “Information geometry and alternating minimization procedures,” Statistics and Decisions, Supplement Issue 1: pp. 205–237, 1984
S.A. Della Pietra and VJ. Della Pietra: “Statistical modeling using maximum entropy”, Workshop on computer vision, Isaac Newton Institute for Mathematical Sciences, Cambridge, UK, October 18-22, 1993. Also, forthcoming IBM report.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jelinek, F. (1995). Two New Approaches to Language Modeling: A Tutorial. In: Ayuso, A.J.R., Soler, J.M.L. (eds) Speech Recognition and Coding. NATO ASI Series, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57745-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive