Abstract
The system described generates a language model for use in the APRIL natural-language parser. The APRIL language model takes the form of a set of typical productions (pairings of mother label with sequence of daughter labels) for each non-terminal category; the system analyses an input by seeking a labelled tree over the words of the input which offers the best fit between each production in the tree and some production of the language model. Previous versions of APRIL used hand-designed language models, but this became a serious research bottleneck. This paper presents a system which uses stochastic optimization to reduce a large set of observed productions to a set of “prototype productions” which are few in number but which nevertheless successfully typify the large observed set.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
E. Aarts and J. Korst 1989 Simulated Annealing and Boltzmann Machines. Wiley.
G.R. Sampson 1994 English for the Computer: The SUSANNE Corpus and Analytic Scheme. Forthcoming from Oxford University Press.
G.R. Sampson et al. 1989 “Natural language analysis by stochastic optimization”. Journal of Experimental and Theoretical Artificial Intelligence 1.271–87.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dennis, M.D., Wallington, A.M., Sampson, G.R. (1994). Stochastic optimization of a probabilistic language model. In: Carrasco, R.C., Oncina, J. (eds) Grammatical Inference and Applications. ICGI 1994. Lecture Notes in Computer Science, vol 862. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58473-0_155
Download citation
DOI: https://doi.org/10.1007/3-540-58473-0_155
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58473-5
Online ISBN: 978-3-540-48985-6
eBook Packages: Springer Book Archive