<?xml version="1.0" standalone="yes"?>
<Paper uid="E99-1051">
  <Title>Robust and Flexible Mixed-Initiative Dialogue for Telephone Services</Title>
  <Section position="3" start_page="0" end_page="287" type="metho">
    <SectionTitle>
1~ Dep. SSR. ETSIT-UPM Spain
2 ROBUST AND FLEXIBLE
SYSTEM
</SectionTitle>
    <Paragraph position="0"> Following the classification of Dialogue Systems proposed by Allen (Allen, 1997), our baseline clialogue system could be described as a system with topic-based performance capabilities, adaptive single task, a minimal pair clarification/correction dialogue manager and fixed mixed-initiative.</Paragraph>
    <Paragraph position="1"> One of the most important objectives of our dialogue manager has been the implementation of a collaborative dialogue model. So the system has to be able to understand all the user actions, in whatever order they appear, and even if the focus of the dialogue has been changed by the user. In order to achieve this, we organize the information in an information tree, controlled by a task knowledge interpreter and we let the data to participate in driving the dialogue. However, to control a mixed-initiative strategy we use three separate sources of information: the user data, the world knowledge embedded in the task structure and the general dialogue acts.</Paragraph>
    <Paragraph position="2"> Therefore, from this preliminar evaluation of the system we found that in order to increase its permormance two major points should be addressed: a) robustness against recognition and parser errors, and b) more flexibility to be able to deal with different user models. We designed four complementary strategies to improve its performance: null  1. To estimate the performance of the speech recognition module. This was done from a count on the number of corrections during previous interactions with the same user.</Paragraph>
    <Paragraph position="3"> 2. To classify each user as belonging to group A or B  that will be described later in the Experimental Results section. This was done combining a normalized average number of utterances per task and the amount of information in each utterance, especially at some particular dialogue points (for example when answering to the question of our previous example).</Paragraph>
    <Paragraph position="4">  3. To include a control module that from the results of steps 1 and 2 defines two different kinds of control management allowing a flexible mixed-initiative strategy: more user initiative for Group A users and high recognition rates, and more restictive strategies for Group B users and/or low recognition performance.</Paragraph>
    <Paragraph position="5"> All of these strategies have been included in our system as it is depicted in Figure 1.</Paragraph>
  </Section>
class="xml-element"></Paper>