<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-1006">
  <Title>Advice-Giving Dialogue&amp;quot; An Integrated System</Title>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
1 The Demonstrator
</SectionTitle>
    <Paragraph position="0"> In its final phase, the project was oriented towards the development of a demonstration prototype, incorporating various ESTEAM-3 16 research results and showing the feasibility of an AGES. The Cooperation Architecture is a conceptual framework for AGES design and a set of mechanisms to support implementation of that design. It is a cooperation architecture because it supports the active cooperation of independent components or modules of the AGES; it is thus the means for integration. Furthermore, it supports the integration of heterogeneous modules through encapsulation of modules as agents, and by providing module-module cooperation using any of three standard interaction models.</Paragraph>
    <Paragraph position="1"> Our dialogue module integrates various subsystems, for example, a natural-language and intention recognition module, an expression generation module and a dialogue planning and management module. Great advances have been made in each of these domains but at present we are dealing only with the tip of the iceberg. In the project ESTEAM- 3 1 6 we chose not to address specific issues such as explanation in great detail (there are many researchers already addressing these problems), but to build a general integrated system aimed at recognizing the user's intentions and answering hhn in an 1This work was supported in part by the Commission of the European Communities as ESPRIT project 316 (ESTEAM- 3,~) understandable way with expert knowledge. We will show how this system is able to incorporate modules which are more specialized in certain domains (problem solver or cooperative data base access).</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 The Agents
</SectionTitle>
    <Paragraph position="0"> The cooperation architecture To provide a design method and to support the efficient implementation of AGES, we have built a special architecture. The architecture aims to keep separate the design and implementation of internal Agent features from external features handling cooperative interaction. The architectural approach to communication allows Agents to share tasks by problem decomposition and to share knowledge by using special Agents for Data and Knowledge Base Management.</Paragraph>
    <Paragraph position="1"> The main problems tackled in defining the architecture concern: * support for the integration of heterogeneous Agents; * control mechanisms for managing the interactions between Agents solving subproblems; * efficient communication between Agents which share or exchange information.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
The Problem Solver
</SectionTitle>
      <Paragraph position="0"> The Problem Solver citehanet incorporates the results of two major research efforts: logic-based modeling and encoding, and explanation generation based on proof trees. The Problem Solver is the module which solves the user's problem{s) in a financial domain and provides proof trees that the Dialogue Manager can use to generate explanations.</Paragraph>
      <Paragraph position="1"> This Problem Solver module is based upon a knowledge representation formalism which integrates and object-oriented approach and logic, and is implemented in Prolog \[1,2\].</Paragraph>
      <Paragraph position="2"> The Cooperative Answering Module In the context of traditional applications devoted to company management, like payroll computation, people or programs who have to access data in a  Database have a very precise definition of the data they want to access. There are many other application.'~ where people want to access data in order to make a decision, or to solve a problem whose solution cannot be found applying a simple algorithm. An important feature of this context, from the point of view of data retrieval, is that users don't have a precise idea of the data which can help them to solve a problem, or to make a decision. The objective of the Cooperative Answering module is to simulate the behavior of a person who wants to help as much as possible an interlocutor who asks them a question. That is, to try to understand why this interlocutor asks this question, and to determine what additional interesting information, not explicitly requested, could be provided in addition to the answer\[3\].</Paragraph>
      <Paragraph position="3"> the Dialogue Manager In the final integrated AGES demonstrator, the main problems are controlling the cooperative functioning of several distinct sources of knowledge, finding ways of representing and reasoning about diverse matters, and integrating the different contributions to perform intelligently a single task, namely advice-giving. The role of the Dialogue Manager is to provide a &amp;quot;friendly&amp;quot;, comprehensible user interface that makes available to the user all the expertise of the various modules of the system in a flexible, uniform fashion \[4,6,7\]. We present in the next section a simple scenario in order to provide its functionahties.</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 A sample dialogue
</SectionTitle>
    <Paragraph position="0"> Let us consider the following session.</Paragraph>
    <Paragraph position="1">  I'd like to buy a car in two years. Ok. An investment plan comprises three subparts: an emergency fund, a fixed-term investment and a long-term investment. How much do you want to invest? $20,000.</Paragraph>
    <Paragraph position="2"> Let's begin with the emergency fund. How much do you want to put into an emergency fund? Let's talk about my car first.</Paragraph>
    <Paragraph position="3"> Ok. How much money do you want to put into the fixed-term investment? Oh, let's say $7,500.</Paragraph>
    <Paragraph position="4"> I recommend that you put the money into a liquid security. Would you like me to propose one? Yes.</Paragraph>
    <Paragraph position="5"> Put your money into a 4.5 % savings account at Sofibanque. Let's return to the emergency fund, now. How much do you want to put in it?  Ok. I recommend that you put the money into a liquid security. Would you like me to propose one? Are there any savings accounts with more than 4.5 % interest? B~rclay's has a savings account at 5 % interest, but it is in England Ok, I'll take Barclay's.</Paragraph>
    <Paragraph position="6"> So, that leaves you with $7,500 for your long-term investment, is this ok? I wanted $10,000.</Paragraph>
    <Paragraph position="7"> If you want an investment plan for $20,000 with an emergency fund of $5,000 and a fixed-term investment of $7,500, it only leaves $7,500 for a long term investment. If you want to put $10,000, then you should modify something else in your plan.</Paragraph>
    <Paragraph position="8"> Could I put $2,500 into the emergency fund? Ok. I recommend for the emergency fund a bank account at Sofibanque earning 4.5%, you can put $10,000 into the long-term investment. What risk-level would you like? What is the risk-level of a long-term investment? null The risk-level is represented by an integer between 1 to 10. It shows the risk you want to have for your portfolio. So, what risk do you choose? What if I put a risk-level of 5? In this case, I recommend ...</Paragraph>
    <Paragraph position="9"> Do you accept? And if the risk-level is 2? In this case, I recommend ...</Paragraph>
    <Paragraph position="10"> Which one do you prefer? The first one Ok. So, to sum up, you want to invest $20,000, with $2,500 in an emergency fund with a delay of 2 days, $7,500 in a fixed-term investment to buy a car in two years, and $10,000 in an long-term investment. Is that right? That's fine Ok. Goodbye!!</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Analysis
</SectionTitle>
      <Paragraph position="0"> From this dialogue, we can easily demonstrate the different points we mentioned above.</Paragraph>
      <Paragraph position="1"> * In sentence 6 the user prefers to begin the discussion with the fixed-term investment, while the system began the discussion with the emergency fund. The system changes tile order of the different topics according to the will of the user and the feasibility of such an exchange.</Paragraph>
      <Paragraph position="2">  (r) In sentence 12, the user does not say &amp;quot;The amount of the emergency fund is $5000&amp;quot; but only &amp;quot;$5000&amp;quot;. The system must understand such an elliptical response. In the same way, the system does not ask &amp;quot;Tell me tile delay of the emergency fund of your Investment plan?&amp;quot; but only &amp;quot;Tell me the delay?&amp;quot;. Normally, the two pa~'ticipants hide a lot of information. They just give sufficient information to have an unambiiguous dialogue. But having a partial knowledge necessitates being able to confirm sometimes what has been understood. In sentence 7, the system asks the user for a confirmation of the value of the fixed-term investment (2 years) which was previously given by him in the sentence 2. The ~ystem has understood that buying a car is equivalent to having a fixed-term investment, but it asks him to verify this supposition. * In sentence 24 the user begins a digression in order to have an explanation about a new term introduced by the system in asking for a value.</Paragraph>
      <Paragraph position="3"> The system has to recognize this new user's intention, cope with (it may be longer than a twoturn dialogue (User, system) as ha the discussion of a given solution) and come back to the previous dialogue.</Paragraph>
      <Paragraph position="4"> * ht sentence 10 the user accepts the system's offer to come up with a detailed investment plan, while in sentence 16 he decides to find out about other possibilities.</Paragraph>
      <Paragraph position="5"> * In sentences 26 - 30 the system and the user explore the implications of a modification of one of the parameters.</Paragraph>
      <Paragraph position="6"> All these considerations appear in any discussions, independently of the topics. There is implicit information (abbreviations, speaking manner) used in a discussion in a given domain. The dialoguer we are building does not handle such implicit information. We focus our attention on the domain-independent aspect of the dialogue organization. However, the advice-giving system must be able to explain what it does and how it does it, and also what the other components it is interfaced with do. We added, therefore, these domain-functionalities in order to implement a system able to help a novice user as well as an experienced one.</Paragraph>
      <Paragraph position="7"> The system has to adapt its utterances and its explanations according to its perception of tile user's knowledge. For instance, when tile system presents a portfolio, it hides irrelevant information for a novice user while it shows it for the experienced one. In the same way, the system tries to use the user's vocabulary. In the example given above, the system uses the word car rather than fixed-term investment in order to hell) the user's understanding.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>