They Know as Much as We Do: Knowledge Estimation and Partner Modelling of Artificial Partners

Abstract

Conversation partners’ assumptions about each other’s knowledge (their partner models) on a subject are important in spoken interaction. However, little is known about what influences our partner models in spoken interactions with artificial partners. In our experiment we asked people to name 15 British landmarks, and estimate their identifiability to a person as well as an automated conversational agent of either British or American origin. Our results show that people’s assumptions about what an artificial partner knows are related to their estimates of what other people are likely to know - but they generally estimate artificial partners to have more knowledge in the task than human partners. These findings shed light on the way in which people build partner models of artificial partners. Importantly, they suggest that people use assumptions about what other humans know as a heuristic when assessing an artificial partner’s knowledge.


Back to Table of Contents