<?xml version="1.0" standalone="yes"?>
<Paper uid="C80-1073">
  <Title>ATNS USED AS A PROCEDURAL DIALOG MODEL</Title>
  <Section position="2" start_page="0" end_page="21" type="intro">
    <SectionTitle>
Introduction
4 Naturally occuring task-oriented dialogs
</SectionTitle>
    <Paragraph position="0"> are the joint product of the interactions of (at least) two participants who know how to cooperate, i. e. who know how to organize - their social interactions - their verbal interactions, and - their task-oriented interactions.</Paragraph>
    <Paragraph position="1"> The amount of such interactions which seem to be necessary in specific task-oriented dialogs may (i) depend on a number of factors given in advance such as: readiness to cooperate (a), preciseness of the task representation (b), amount of mutually shared task-specific knowledge (c), amount of knowledge about the other participant (d) and personal factors as for example competence and (self-) confidence (e); (ii) depend on procedures apt to modify these factors (a - e) in an efficient and positive way; (iii) depend on procedures used for task resolution and result explanation. null Participants of naturally occuring task-oriented dialogs are able to make use of these factors and procedures in a skillful and flexible way, but such properties are still lacking even in experimental dialog systems.</Paragraph>
    <Paragraph position="2"> In past natural language processing research considerable efforts have been made to process the structures underlying sentences or texts. Procedures have been developed which build up deep structures of sentences or which determine macro-structures or event skripts ('frames') underlying texts. In the next two years special efforts will be made to process the structures underlying task-oriented dialogs.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Representation of Interactional
Knowledge
</SectionTitle>
      <Paragraph position="0"> In coversation analysis, systematic accounts of the sequential organization of dialog interactions have been developed, e. g. for turn taking, for opening sequences, for closing or repair sequences 7 or for different types of task-oriented verbal interaction as a whole (e. g. giving advice, directions, explanations) 12 But these accounts have only Deen of a structural type, not of a procedural type. A formal representation has rarely been attempted 6 and an integration or interaction of different knowledge sources is generally not considered.</Paragraph>
      <Paragraph position="1">  --487--In the subsequent sections we will argue for a level of representation guiding the social interactional and the verbal interactional aspects of task-oriented dialogs. A personal belief or knowledge component will use information of this interactional level together with information of a task level as well as information of a sentence/text level. We will argue for a procedural representation of interactional knowledge and we think that the usefulness of ATNS I0'3 for such a representation should be examined in more detail.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="21" type="sub_section">
      <SectionTitle>
'Parsing Interactions'
</SectionTitle>
      <Paragraph position="0"> The approach presented here differs from other computational dialog models in the following way: - A dialog model is not based on an un2 derlying dialog prototype specifying essentially task-oriented information.</Paragraph>
      <Paragraph position="1"> It is claimed that the social interactional and the verbal interactional aspects of task-oriented dialogs are important enough to be represented in a detailed way on a special level.</Paragraph>
      <Paragraph position="2"> - Dialog proporties are not only examined by problem solving techniques I. Instead, extended parsing techniques are used in 'parsing interactions' and they are supposed to be helpful in determining the interactional structure underlying utterances.</Paragraph>
      <Paragraph position="3"> Let us further specify the kind of interactional knowledge which participants of certain types of task-oriented dialogs are supposed to have as well as ways to represent it. The participants will generally know how to manage the social, the verbal and the task-oriented interactions. They will generally know about several rather invariant, components of a certain type of task-oriented dialogs as well as of a normal sequence of these components. They know about the detailed (alternative) structures of each component, the choice of which may depend on factors as were mentioned above(a - e).</Paragraph>
      <Paragraph position="4"> They know  - how to initiate a social contact/a verbal interaction and how to respond positively/negatively to this initiative; null - how to continue/to maintain an interaction, null - how to signalize interest, competence or difficulties of) understanding, - how to organize turn-taking, - how to initiate the termination of a social contact/a verbal interaction and how to respond positively or negatively to it.</Paragraph>
      <Paragraph position="5"> Part of this knowledge may be described as sequences of social/verbal inter- null actions, formally to be represented as connected (sub-) networks of an ATN.</Paragraph>
      <Paragraph position="6"> I. e. social/verbal interaction is seen as a process of path selection of (at least) two participants in a network of states and state transitions. These (sub-) networks should be set up on an empirical basis (recordings of naturally occuring task-oriented dialogs).</Paragraph>
      <Paragraph position="7"> An Example Some properties of the interactional knowledge mentioned above may be represented in an ATN in a straightforward way, whereas the representation of others seem less straightforward.</Paragraph>
      <Paragraph position="8"> Constituents Let us assume that some types of information-giving dialogs may be assigned a  network structure with the following constituents of social/verbal interaction: null</Paragraph>
      <Paragraph position="10"> Each (sub-)network represents sequences of interaction - on the level of a dialog type (a), - on the level of speech act sequences (b), or - on the level of turn-taking organization (c).</Paragraph>
      <Paragraph position="11">  The arcs indicate (alternative) state transitions/(alternative) courses of interaction. They may be marked or unmarked ('JUMPs').</Paragraph>
      <Paragraph position="12"> According to fig. I a dialog interaction  may start: - with a contact initiating utterance (&amp;quot;EXCUSE ME ...&amp;quot;), level a; - with a question introducer (&amp;quot;MAY I ASK YOU ...&amp;quot;) level b; - with a task-specific question (&amp;quot;WHERE DO I FIND ...&amp;quot;), level b; - with a 'turn introducer' (&amp;quot;YES&amp;quot;I &amp;quot;...&amp;quot;) ,  level c.</Paragraph>
      <Paragraph position="13"> Possible actions may be skipped (cf--~4--~arrow), repeated (loons;iteration) or some sequences nay ~e embedded into other sequences (cf. QUESTION/ ANSWER arc in the QUESTION/ANSWER subnetwork; recursion).</Paragraph>
      <Paragraph position="14"> These subnetworks are connected to other networks with the same type of information or with other types of information: null linguistic information in order to recognize/generate different forms (e. g. to initiate a contact, to introduce questions, topass turns) or direct/ indirect ways to ask a question (&amp;quot;9~ERE</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>