Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Evaluating Hierarchical Hybrid Statistical Language Models

Lucian Galescu, James Allen

University of Rochester, USA

We introduce in this paper a hierarchical hybrid statistical language model, represented as a collection of local models plus a general model that binds together the local ones. The model provides a unified framework for modelling language both above and below the word level, and we exemplify with models of both kinds for a large vocabulary task domain. To our knowledge this is the first paper to report an extensive evaluation of the improvements achieved from the use of local models within a hierarchical framework in comparison with a conventional word-based trigram model.


Full Paper

Bibliographic reference.  Galescu, Lucian / Allen, James (2000): "Evaluating hierarchical hybrid statistical language models", In ICSLP-2000, vol.2, 963-966.