Bibliographic Metadata
Bibliographic Metadata
- TitleUnveiling the Information State with a Bayesian Model of the Listener
- Author
- Published
- LanguageEnglish
- Document typeConference Proceedings
- Keywords
- URN
Restriction-Information
- The document is publicly available on the WWW
Links
- Social MediaShare
- ReferenceNo Reference available
- IIIF
Files
Classification
Abstract
Attentive speaker agents – artificial conversational agents that can attend to and adapt to listener feedback – need to attribute a mental ‘listener state’ to the user and keep track of the grounding status of their own utterances. We propose a joint model of listener state and information state, represented as a dynamic Bayesian network, that can capture the influences between dialogue context, user feedback, the mental listener state and the information state, providing an estimation of grounding.
Stats
- The PDF-Document has been downloaded 5 times.