dc.contributor.advisor | VOGEL, CARL | |
dc.contributor.author | COWDEROY, GRACE | |
dc.date.accessioned | 2018-11-30T08:47:09Z | |
dc.date.available | 2018-11-30T08:47:09Z | |
dc.date.issued | 2018 | en |
dc.date.submitted | 2018 | |
dc.identifier.citation | COWDEROY, GRACE, Partitioning POMDPs for multiple input types, and their application to dialogue managers, Trinity College Dublin.School of Computer Science & Statistics, 2018 | en |
dc.identifier.other | Y | en |
dc.identifier.uri | http://hdl.handle.net/2262/85443 | |
dc.description | APPROVED | en |
dc.description.abstract | This research looks at the POMDP models used for dialogue management within Spoken Dialogue
Systems (SDS). In particular, it examines the difficulty of handling multimodal inputs. It proposes a
generalisation of the POMDP model in order to tackle this.
This model is shown, via a Car Advisory system, to improve tractability for multimodal inputs. | en |
dc.language.iso | en | en |
dc.publisher | Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science | en |
dc.rights | Y | en |
dc.subject | partitioning POMDPs | en |
dc.subject | car advisory system | en |
dc.subject | POMDP | en |
dc.subject | dialogue manager | en |
dc.subject | multimodal input | en |
dc.title | Partitioning POMDPs for multiple input types, and their application to dialogue managers | en |
dc.type | Thesis | en |
dc.type.supercollection | thesis_dissertations | en |
dc.type.supercollection | refereed_publications | en |
dc.type.qualificationlevel | Masters (Research) | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/cowderog | en |
dc.identifier.rssinternalid | 193340 | en |
dc.rights.ecaccessrights | openAccess | |
dc.contributor.sponsor | Adapt Centre | en |