Intonational Boundaries, Speech Repairs and Discourse Markers: Modeling Spoken Dialog

dc.creatorHeeman, Peter A.
dc.creatorAllen, James F.
dc.date1997-04-23
dc.date.accessioned2026-07-07T09:10:46Z
dc.date.available2026-07-07T09:10:46Z
dc.descriptionTo understand a speaker's turn of a conversation, one needs to segment it into intonational phrases, clean up any speech repairs that might have occurred, and identify discourse markers. In this paper, we argue that these problems must be resolved together, and that they must be resolved early in the processing stream. We put forward a statistical language model that resolves these problems, does POS tagging, and can be used as the language model of a speech recognizer. We find that by accounting for the interactions between these tasks that the performance on each task improves, as does POS tagging and perplexity.
dc.description8 pages, 3 postscript figures
dc.identifierhttps://arxiv.org/abs/cmp-lg/9704008
dc.identifierhttp://arxiv.org/abs/cmp-lg/9704008
dc.identifierIn proceedings of ACL/EACL'97
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151447
dc.subjectComputation and Language
dc.titleIntonational Boundaries, Speech Repairs and Discourse Markers: Modeling Spoken Dialog
dc.typetext

Files

Collections