Domain Adaptation with Clustered Language Models

dc.creatorUeberla, Joerg P.
dc.date1997-03-04
dc.date.accessioned2026-07-07T09:10:44Z
dc.date.available2026-07-07T09:10:44Z
dc.descriptionIn this paper, a method of domain adaptation for clustered language models is developed. It is based on a previously developed clustering algorithm, but with a modified optimisation criterion. The results are shown to be slightly superior to the previously published 'Fillup' method, which can be used to adapt standard n-gram models. However, the improvement both methods give compared to models built from scratch on the adaptation data is quite small (less than 11% relative improvement in word error rate). This suggests that both methods are still unsatisfactory from a practical point of view.
dc.descriptionpreprint - to appear in ICASSP 97
dc.identifierhttps://arxiv.org/abs/cmp-lg/9703001
dc.identifierhttp://arxiv.org/abs/cmp-lg/9703001
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151438
dc.subjectComputation and Language
dc.titleDomain Adaptation with Clustered Language Models
dc.typetext

Files

Collections