<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1068">
  <Title>A CD-ROM Retrieval System with Multiple Dialogue Agents</Title>
  <Section position="2" start_page="0" end_page="400" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recently, research into 'multi-agent systenF is increasing. The multi-agent systeln is now one of the promising solutions to achieve a complicated system (Maes, 91; Nishida and Takada, 93; Nagao aud Takeuchi, 94).</Paragraph>
    <Paragraph position="1"> The multi-agent system which silnulates co-operation between qmman-agents' is realized by an integration of simplified autonomous flmctions. And ms a result it achieves a complicated system in total. It also has a latent potential to make a very flexible system.</Paragraph>
    <Paragraph position="2"> Thus, we believe that if we introduce the concept of the nmlti-agent system into a dialogue system, we are able to construct a more sophisticated system which is able to treat various linguistic phenomena and to understand or to solw., nmre cmnplicated problems.</Paragraph>
    <Paragraph position="3"> Focusing on dialogue systelns, while most current dialogue systems can treat only one domain (a small world for a single service), some research(Goddeau et al., 94; Nalnba et 31., 94) which aims at increasing the domains, what is called a transportable system(Grosz, 83; Paris, 89) are lmW on-going. Ill such systems, information re.trieval across multil)le domains is realized using the relational databases. However in our systeln, it is difficult to retrieve information across nmltipie donlains, I)ecause the information is retrieved from CD-ROMs in which a large amount of texts are contained, 1)y using full-text retrieval techniques. null And while there are robust and useful strategies in certain goals, there isn't an all-powerful sterategy which covers all goals. If a robust strategy in a certain goal is introduced into tile system, the user misunderstands that the system hKs an all-powerful strategy. Thus, in our system the user sometimes gets into trouble as follows: * the user misunderstands that the information contained across several data sources call be obtained at once.</Paragraph>
    <Paragraph position="4"> * the user is confused between a certain retrieval strategy which is robust in a certain goal and another siml)le but rather redmldant strategy.</Paragraph>
    <Paragraph position="5"> Furthernmre, it is difficult to manage a discourse involving multiple goals in current diMogue systems. This is because most current systems aren't robust enough for anaphora and they are able to manage only a single and simple context.</Paragraph>
    <Paragraph position="6"> This sometimes causes the following problem: * the user has to manage the nmltiple contexts involving multiple goals, because the system only ma.nages a single context. And ithis makes it hard for the user to use the system.</Paragraph>
    <Paragraph position="7"> As the result, the user also gets lost in the system. In this paper, we focus on how to make the user aware of what the system Call or cannot do.</Paragraph>
    <Paragraph position="8"> Thus, we propose a nevC/ dialogue system with multiple agents, in which we introduce the concept of multi-agent system into our dialogue system. Ill our system, three types of dialogue agents are re~ alized: 1) for each domain, 2) for each strategy and 3) for each context. These agents take turns and play their roles according to the discourse situations. With these agents, our system will haw; the following characteristics: * the domain agents mM~e the user aware of the 1)oundary between unintegrated domains.</Paragraph>
    <Paragraph position="9"> * the strategy agents make the user aware of the difference, between the don lain oriented strategies.</Paragraph>
    <Paragraph position="10">  * the context agents make it ea.sy for the user to deal with tit(; coml)licatcd discourse involving multiple goals.</Paragraph>
    <Paragraph position="11"> In this pal)er, we first Cxl)lain our l)aseline spoken dialogue systeln TARSAN which deM with multiple domains. Secondly, we describe the problems which arise when wc extend the system into multiple domains. After that, we propose a new dialogue systeln with nmltiple diMogue agents.</Paragraph>
    <Paragraph position="12"> We ,also describe the results of the examinations on the l)rOl)OSC(l system. Finally, we conclude the pal)cr.</Paragraph>
  </Section>
class="xml-element"></Paper>