Abstract
The talk will concern several ideas that combat the sparse data problem of language modeling. All alleviate it, neither solves it. These ideas are: equivalence classification of histories, positional clustering (different cluster systems for different n-gram positions), use of linguistic classes (e.g., Wordnet), class constraints in maximum entropy estimation, random forests, and neural network classification. An interesting problem that must be faced is as follows: words that are sparse and need to be classified do not have sufficient statistics to indicate their appropriate class membership.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsAuthor information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jelinek, F. (2003). Combating the Sparse Data Problem of Language Modelling. In: Matoušek, V., Mautner, P. (eds) Text, Speech and Dialogue. TSD 2003. Lecture Notes in Computer Science(), vol 2807. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39398-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-540-39398-6_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20024-6
Online ISBN: 978-3-540-39398-6
eBook Packages: Springer Book Archive