Requirements for belief models in cooperative dialogue

Jasper A. Taylor, Jean Carletta, Chris Mellish

Research output: Contribution to journalArticlepeer-review

Abstract

Models of rationality typically rely on underlying logics that allow simulated agents to entertain beliefs about one another to any depth of nesting. Such models seem to be overly complex when used for belief modelling in environments in which cooperation between agents can be assumed, i.e., most HCI contexts. We examine some existing dialogue systems and find that deeply-nested beliefs are seldom supported, and that where present they appear to be unnecessary except in some situations involving deception.
Original languageEnglish
Pages (from-to)23-68
Number of pages46
JournalUser Modeling and User-Adapted Interaction
Volume6
Issue number1
DOIs
Publication statusPublished - 1996

Fingerprint

Dive into the research topics of 'Requirements for belief models in cooperative dialogue'. Together they form a unique fingerprint.

Cite this