<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1304">
  <Title>Interactive Question Answering and Constraint Relaxation in Spoken Dialogue Systems</Title>
  <Section position="3" start_page="0" end_page="28" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Information presentation is an important issue when designing a dialogue system. This is especially true when the dialogue system is used in a high-stress environment, such as driving a vehicle, where the user is already occupied with the driving task. In this paper, we explore efficient dialogue strategies to address these issues, and present implemented knowledge management, dialogue and generation components that allow cognitively overloaded users - see (Weng et al., 2004), for example - to obtain information from the dialogue system in a natural way. We describe a knowledge manager that provides factual and ontological information, a content optimizer that regulates the amount of information, and a generator that realizes the selected content. The domain data is divided between domain-specific ontologies and a database back-end. We use the system for both restaurant selection and MP3 player tasks, and conducted experiments with 20 subjects.</Paragraph>
    <Paragraph position="1"> There has been substantial previous work on information presentation in spoken dialogue systems. (Qu and Green, 2002) also present a constraint-based approach to cooperative information dialogue. Their experiments focus on over-constrained queries, whereas we also deal with underconstrained ones. Moreover, we guide the user through the dialogue by making suggestions about query refinements, which serve a similar r^ole to the conditional responses of (Kruijff-Korbayova et al., 2002). (Hardy et al., 2004) describe a dialogue system that uses an error-correcting database manager for matching caller-provided information to database entries. This allows the system to select the most likely database entry, but, in contrast to our approach, does not modify constraints at a more abstract level. In contrast to all the approaches mentioned above, our language generator uses overgeneration and ranking techniques (Langkilde, 2000; Varges and Mellish, 2001).</Paragraph>
    <Paragraph position="2"> This facilitates variation and alignment with the user utterance.</Paragraph>
    <Paragraph position="3"> A long-standing strand of research in NLP is in natural language access to databases (Androutsopoulos et al., 1995). It mainly focused on mapping natural language input to database queries.</Paragraph>
    <Paragraph position="4"> Our work can be seen as an extension of this work by embedding it into a dialogue system and allowing the user to refine and relax queries, and to engage in clarification dialogs. More recently, work on question answering (QA) is moving toward interactive question answering that gives the user a greater role in the QA process (HLT, forthcoming). QA systems mostly operate on free text whereas we use a relational database. (Thus, one needs to 'normalize' the information contained in free text to use our implemented system without further adaption.)  In the following section, we give an overview of the dialogue system. We then describe the knowledge management, dialogue and generation components in separate sections. In section 6 we present evaluation results obtained from a user study. This is followed by a discussion section and conclusions.</Paragraph>
  </Section>
class="xml-element"></Paper>