Variable Word Rate N-grams

dc.creatorGotoh, Yoshihiko
dc.creatorRenals, Steve
dc.date2000-03-29
dc.date.accessioned2026-07-07T03:16:08Z
dc.date.available2026-07-07T03:16:08Z
dc.descriptionThe 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%.
dc.description4 pages, 4 figures, ICASSP-2000
dc.identifierhttps://arxiv.org/abs/cs/0003081
dc.identifierhttp://arxiv.org/abs/cs/0003081
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30238
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleVariable Word Rate N-grams
dc.typetext

Files

Collections