Semantic filtering by inference on domain knowledge in spoken dialogue systems

Simple item page
dc.creatorBallim, Afzal
dc.creatorPallotta, Vincenzo
dc.date2004-10-23
dc.date.accessioned2026-07-07T03:21:54Z
dc.date.available2026-07-07T03:21:54Z
dc.descriptionGeneral natural dialogue processing requires large amounts of domain knowledge as well as linguistic knowledge in order to ensure acceptable coverage and understanding. There are several ways of integrating lexical resources (e.g. dictionaries, thesauri) and knowledge bases or ontologies at different levels of dialogue processing. We concentrate in this paper on how to exploit domain knowledge for filtering interpretation hypotheses generated by a robust semantic parser. We use domain knowledge to semantically constrain the hypothesis space. Moreover, adding an inference mechanism allows us to complete the interpretation when information is not explicitly available. Further, we discuss briefly how this can be generalized towards a predictive natural interactive system.
dc.description6 pages
dc.identifierhttps://arxiv.org/abs/cs/0410060
dc.identifierhttp://arxiv.org/abs/cs/0410060
dc.identifierProceedings of the LREC 2000 Workshop "From spoken dialogue to full natural interactive dialogue. Theory, empirical analysis and evaluation", May 29th, 2000 Athen, Greece
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32388
dc.subjectComputation and Language
dc.subjectArtificial Intelligence
dc.subjectHuman-Computer Interaction
dc.subjectInformation Retrieval
dc.subjectH.5.2;H.3.1;H.3.4
dc.titleSemantic filtering by inference on domain knowledge in spoken dialogue systems
dc.typetext

Files

Collections

arXiv