Show simple item record

dc.contributor.authorGotoh, Yoshihiko
dc.contributor.authorRenals, Steve
dc.coverage.spatial4en
dc.date.accessioned2006-05-11T13:09:03Z
dc.date.available2006-05-11T13:09:03Z
dc.date.issued2000-06
dc.identifier.citationAcoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on, Volume 3, 5-9 June 2000 Page(s):1591 - 1594en
dc.identifier.otherDigital Object Identifier 10.1109/ICASSP.2000.861992
dc.identifier.urihttp://ieeexplore.ieee.org/
dc.identifier.urihttp://hdl.handle.net/1842/979
dc.description.abstractThe rate of occurrence of words is not uniform but varies from document to document. Despite this observation, parameters for conventional N-gram language models are usually derived using the assumption of a constant word rate. In this paper we investigate the use of variable word rate assumption, modelled by a Poisson distribution or a continuous mixture of Poissons. We present an approach to estimating the relative frequencies of words or N-grams taking prior information of their occurrences into account. Discounting and smoothing schemes are also considered. Using the Broadcast News task, the approach demonstrates a reduction of perplexity up to 10%en
dc.format.extent400480 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEEen
dc.titleVariable word rate N-gramsen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record