<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0611">
  <Title>I I DISTANCE ZONE I \ %alce=-=ource takeo-de=tinatPSon I I SOURCE DESTINATION I TOTAL-COST / I / I</Title>
  <Section position="1" start_page="0" end_page="53" type="abstr">
    <SectionTitle>
1 Motivation
</SectionTitle>
    <Paragraph position="0"> A common feature of a number of current spoken dialogue systems for information retrieval is that little emphasis is placed on the generation of system contributions to the dialogue. In these systems, utterances have mostly been produced from templates, see for instance (Whittaker and Attwater 1994; Blomberg et al. 1993; Oerder and Aust 1993; Meng et al. 1996). This is a valid approach in system initiative type systems and in systems where utterances stand in a one-to-one relation to communicative goals. In mixed initiative systems, however, user and system might both lead the dialogue by providing several pieces of information and pursuing several different goals within one utterance. Hence, in this kind of dialogue we cannot predict what information the user chooses to provide, and hence cannot predict the system's response. We argue that in any system of reasonable size, the number of templates would be too large to determine a priori. Instead, in order to achieve efficient and cooperative dialogue, system utterances must be generated using natural language generation (NLG) techniques.</Paragraph>
    <Paragraph position="1"> NLG has been used by, for instance, (Pan and McKeown 1996; Sadek et al. 1996), but they put emphasis on generation of system answers, i.e. on offering and providing information. We are concerned with utterances requesting specific information. (Sadek et al. 1996) also generate requests, but they are mostly of a general nature, and the sample dialogue in their paper suggests that the system's requests for specific information can only realize one communicative goal at a time.</Paragraph>
    <Paragraph position="2"> In several recent systems (e.g., (Allen et al. 1996; Sadek et al. 1996)), confirmation of information that the system acquires from the user (variables) is mostly avoided. This might be a valid approach as their number of variables is small, but we think that it will lead to frustrating dialogues when several variables are needed. Consider the following interaction, where the system actually misrecognized all the values provided by the user. User: &amp;quot;How much is a call from Bonn to Homburg at 8 o'clock?&amp;quot; Sys: &amp;quot;A call from Berlin to Hamburg at 1800 costs 36 Pfennig per minute.&amp;quot; It would be very hard to recover from this situation and the user would most likely never call again.</Paragraph>
    <Paragraph position="3"> *The author is a visiting researcher in the speech pro- cessing group FZ131, Deutsche Telekom. Authors are in opposite alphabetical order this time.</Paragraph>
    <Paragraph position="4"> In our domain (calculation of the price of phone calls), the system must acquire several variables--with sometimes ambiguous values. Therefore confirmation and disambiguation questions are necessary, and hence we have a larger number of communicative goals to satisfy than the afore mentioned systems. But, if we were to designate a single utterance for each communicative goal, we would quickly end up with inefficient and annoying dialogues like the following: Sample dialogue 1  A. Sys: Do you want the rate or the total cost of a call? B. Usr: How much is a call to Frankfurt, please. C. Sys: Do you want the rate or the total cost of a call? D. Usr: The rate of a call to Frankfurt. E. Sys: Do you want the rate of a call? F. Usr: Yes, to Frankfurt, please. G. Sys: What is the destination of your call? H. Usr: Frankfurt! I. Sys: Is the destination of your call Frankfurt? J. Usr: Yess!! K. Sys: Frankfurt am Main or Frankfurt an der Oder? L. Usr: Frankfurt am MAAAAIIIN!!!  To avoid such uncooperative dialogues, a system has to be able to interpret additional information provided by the user, as, for instance, in move D in dialogue 1.</Paragraph>
    <Paragraph position="5"> Further, system responses must be efficient. Humans achieve efficiency by pursuing several goals at a time instead of dealing with single goals in a strict sequential order. In our approach, we apply this observation to the design of information systems, hoping that it results in an interaction as illustrated in dialogue 2.</Paragraph>
    <Paragraph position="6"> Here, some goals are expressed implicitly (e.g., confirmation in utterance C), while others are omitted (e.g., asking for the destination).</Paragraph>
    <Paragraph position="7"> Sample dialogue 2 A. Sys: Do you want the rate or the total cost of a call? B. Usr: How much is a call to Frankfurt, please. C. Sys: The rate or the total cost of a call to Frankfurt? D. Usr: The rate, please. E Sys: Frankfurt am Main or Frankfurt an der Oder? D. Usr: Am Main.</Paragraph>
    <Paragraph position="8"> In this paper, we describe an initial realization of such a cooperative and efficient mixed initiative dialogue system. In particular, we discuss system utterances whose primary goal is to acquire information of various kinds, since these occur frequently in our domain. Building on results in (Hagen 1997), we develop heuristics for jointly expressing several communicative goals in one utterance, thus responding to the requirements of the task at hand and to the user initiative at the same time. A prototypical system that answers  for the TESADIS telephone rate inquiry system.</Paragraph>
    <Paragraph position="9"> queries about the cost of telephone calls is currently being implemented.</Paragraph>
  </Section>
class="xml-element"></Paper>