Variable word rate N-grams

Yoshihiko Gotoh, Steve Renals

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The 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%
Original languageEnglish
Title of host publicationProceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing
Subtitle of host publicationICASSP '00
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)0-7803-6293-4
Publication statusPublished - 2000
Event2000 IEEE International Conference! on Acoustics, Speech, and Signal Processing - Hilton Hotel and Convention Center, Istanbul, Turkey
Duration: 5 Jun 20009 Jun 2000


Conference2000 IEEE International Conference! on Acoustics, Speech, and Signal Processing


Dive into the research topics of 'Variable word rate N-grams'. Together they form a unique fingerprint.

Cite this