Statistical language modeling using a variable context length

  title={Statistical language modeling using a variable context length},
  author={Reinhard Kneser},
In this paper we investigate statistical language models with a variable context length. For such models the number of relevant words in a context is not xed 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-o distribution can improve the language models… CONTINUE READING

4 Figures & Tables



Citations per Year

80 Citations

Semantic Scholar estimates that this publication has 80 citations based on the available data.

See our FAQ for additional information.