Abstract
In this paper we investigate statistical language models with avariable context length. For such models the number of relevantwords in a context is not fixed as in conventional M-gram models but depends on the context itself. We develop a measure for the quality of variable-length models and present a pruning algorithm for the creation of such models, based on this measure. Further we address the question how the use of a special backing-off distribution can improve the language models....

This publication has 7 references indexed in Scilit: