On the use of expectations for detecting and repairing human-machine miscommunication

dc.creatorDanieli, Morena
dc.date1997-11-19
dc.date.accessioned2026-07-07T02:36:08Z
dc.date.available2026-07-07T02:36:08Z
dc.descriptionIn this paper I describe how miscommunication problems are dealt with in the spoken language system DIALOGOS. The dialogue module of the system exploits dialogic expectations in a twofold way: to model what future user utterance might be about (predictions), and to account how the user's next utterance may be related to previous ones in the ongoing interaction (pragmatic-based expectations). The analysis starts from the hypothesis that the occurrence of miscommunication is concomitant with two pragmatic phenomena: the deviation of the user from the expected behaviour and the generation of a conversational implicature. A preliminary evaluation of a large amount of interactions between subjects and DIALOGOS shows that the system performance is enhanced by the uses of both predictions and pragmatic-based expectations.
dc.description7 pages, LaTeX, uses aaai.sty
dc.identifierhttps://arxiv.org/abs/cmp-lg/9711008
dc.identifierhttp://arxiv.org/abs/cmp-lg/9711008
dc.identifierProceedings of AAAI-96 Workshop on Detecting, Preventing, and Repairing Human-Machine Miscommunications, Portland, OR, pp. 87-93
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/15806
dc.subjectComputation and Language
dc.titleOn the use of expectations for detecting and repairing human-machine miscommunication
dc.typetext

Files

Collections