Combining semantic and syntactic structure for language modeling

dc.creatorBod, Rens
dc.date2001-10-24
dc.date.accessioned2026-07-07T03:17:50Z
dc.date.available2026-07-07T03:17:50Z
dc.descriptionStructured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute to significantly improved word error rate, and that a data-oriented parsing model trained on semantically and syntactically annotated data can exploit these dependencies. This paper also contains the first DOP model trained by means of a maximum likelihood reestimation procedure, which solves some of the theoretical shortcomings of previous DOP models.
dc.description4 pages
dc.identifierhttps://arxiv.org/abs/cs/0110051
dc.identifierhttp://arxiv.org/abs/cs/0110051
dc.identifierProceedings ICSLP'2000, Beijing, China
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30875
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleCombining semantic and syntactic structure for language modeling
dc.typetext

Files

Collections