Abstract | ||
---|---|---|
A Situated Conversational Agent (SCA) is an agent that engages in dialog about the context within which it is embedded. Situated dialog is characterized by its deep connection to the embedding context, and the precise cross-timing of linguistic and non-linguistic ac- tions. This paper describes initial research into the con- struction of an SCA that engages in dialog about collab- orative physical tasks, in which agents engage in dialog with the joint goal of manipulating the physical context in some manner. Constructing an SCA that can inter- act naturally in such tasks requires an agent with the ability to interleave planning, action, and observation while operating in a partially observable environment. Consequently, I propose to model an SCA as a Partially Observable Markov Decision Process (POMDP). |
Year | Venue | Keywords |
---|---|---|
2007 | AAAI | observable environment,physical context,conversational agent,non-linguistic action,situated conversational agent,joint goal,deep connection,embedding context,initial research,collaborative physical task,partially observable markov decision |
Field | DocType | Citations |
Situated,Dialog box,Physical context,Embedding,Observable,Partially observable Markov decision process,Computer science,Artificial intelligence,Dialog system | Conference | 0 |
PageRank | References | Authors |
0.34 | 2 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
William Thompson | 1 | 6 | 2.97 |