<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1070">
  <Title>Towards a Model of Face-to-Face Grounding</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> An essential part of conversation is to ensure that the other participants share an understanding of what has been said, and what is meant. The process of ensuring that understanding - adding what has been said to the common ground - is called grounding [1]. In face-to-face interaction, nonverbal signals as well as verbal participate in the grounding process, to indicate that an utterance is grounded, or that further work is needed to ground.</Paragraph>
    <Paragraph position="1"> Figure 1 shows an example of human face-to-face conversation. Even though no verbal feedback is provided, the speaker (S) continues to add to the directions. Intriguingly, the listener gives no explicit nonverbal feedback - no nods or gaze towards S. S, however, is clearly monitoring the listener's behavior, as we see by the fact that S looks at her twice (continuous lines above the words). In fact, our analyses show that maintaining focus of attention on the task (dash-dot lines underneath the words) is the listener's public signal of understanding S's utterance sufficiently for the task at hand. Because S is manifestly attending to this signal, the signal allows the two jointly to recognize S's contribution as grounded. This paper provides empirical support for an essential role for nonverbal behaviors in grounding, motivating an architecture for an embodied conversational agent that can establish common ground using eye gaze, head nods, and attentional focus.</Paragraph>
    <Paragraph position="2"> Although grounding has received significant attention in the literature, previous work has not addressed the following questions: (1) what predictive factors account for how people use non-verbal signals to ground information, (2) how can a model of the face-to-face grounding process be used to adapt dialogue management to face-to-face conversation with an embodied conversational agent. This paper addresses these issues, with the goal of contributing to the literature on discourse phenomena, and of building more advanced conversational humanoids that can engage in human conversational protocols.</Paragraph>
    <Paragraph position="3"> In the next section, we discuss relevant previous work, report results from our own empirical study and, based on our analysis of conversational data, propose a model of grounding using both verbal and nonverbal information, and present our implementation of that model into an embodied conversational agent. As a preliminary evaluation, we compare a user interacting with the embodied conversational agent with and without grounding.</Paragraph>
  </Section>
class="xml-element"></Paper>