Modeling situated conversational agents as partially observable markov decision processes

William Karl Thompson*, Darren Gergle

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

A Situated Conversational Agent (SCA) is an agent that engages in dialog about the context within which it is embedded. An SCA is distinguished from non-situated conversational agents by an intimate connection of the agent's dialog to its embedding context, and by intricate dependencies between its linguistic and physical actions. Constructing an SCA that can interact naturally with users while engaged in collaborative physical tasks requires the agent to interleave decision making under uncertainty, action execution, and observation while maximizing expected utility over a sequence of interactions. These requirements can be fulfilled by modeling an SCA as a partially observable Markov decision process (POMDP). We show how POMDPs can be used to formalize and implement psycholinguistic proposals on how situated dialog participants collaborate in order to make and ground dialog contributions.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th International Conference on Intelligent User Interfaces 2008, IUI'08
Pages401-404
Number of pages4
DOIs
StatePublished - Dec 15 2008
Event13th International Conference on Intelligent User Interfaces 2008, IUI'08 - Maspalomas, Gran Canaria, Spain
Duration: Jan 13 2008Jan 16 2008

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Other

Other13th International Conference on Intelligent User Interfaces 2008, IUI'08
CountrySpain
CityMaspalomas, Gran Canaria
Period1/13/081/16/08

Keywords

  • Decision-theoretic planning
  • Situated conversational agents

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Modeling situated conversational agents as partially observable markov decision processes'. Together they form a unique fingerprint.

Cite this