<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-2027">
  <Title>Evaluating Automatic Dialogue Strategy Adaptation for a Spoken Dialogue System</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recent advances in speech technologies have enabled spoken dialogue systems to employ mixed initiative dialogue strategies (e.g. (Allen et al., 1996; Sadek et al., 1996; Meng et al., 1996)). Although these systems interact with users in a manner more similar to human-human interactions than earlier systems employing system initiative strategies, their response strategies are typically selected using only local dialogue context, disregarding dialogue history. Therefore, their gain in naturalness and performance under optimal conditions is often overshadowed by their inability to cope with anomalies in dialogues by automatically adapting dialogue strategies. In contrast, Figure 1 shows a dialogue in which the system automatically adapts dialogue strategies based on the current user utterance and dialogue history. 1 After failing to obtain a valid response to an information-seeking query in utterance (4), the system adapted dialogue strategies to provide additional information in (6) that assisted the user in responding to the query. Furthermore, after the user responded to a limited system prompt in (10) with a fully-specified query in (11), implicitly indicating her intention to take charge of the problem-IS and U indicate system and user utterances, respectively. The words appearing in square brackets are the output from the Lucent Automatic Speech Recognizer (Reichl and Chou, 1998; Ortmanns et al., 1999), configured to use class-based probabilistic n-gram language models. The task and dialogue initiative annotations are explained in Section 2.1.</Paragraph>
    <Paragraph position="1"> solving process, the system again adapted strategies, hence providing an open-ended prompt in (13).</Paragraph>
    <Paragraph position="2"> Previous work has shown that dialogue systems in which users can explicitly change the system's dialogue strategies result in better performance than nonadaptable systems (Litman and Pan, 1999). However, no earlier system allowed for initiative-oriented automatic strategy adaptation based on information dynamically extracted from the user's spoken input. In this paper, we briefly introduce MIMIC, a mixed initiative spoken dialogue system that automatically adapts dialogue strategies. We then describe two experiments that evaluated the effectiveness of MIMIC's mixed initiative and automatic adaptation capabilities. Our results show that, when analyzed along the performance dimension, MIMIC's mixed initiative and automatic adaptation features lead to more efficient dialogues and higher user satisfaction. Moreover, when analyzed along the discourse and initiative dimensions, MIMIC's adaptation capabilities result in dialogues in which system behavior better matches user expectations and dialogue anomalies are resolved more efficiently.</Paragraph>
  </Section>
class="xml-element"></Paper>