<?xml version="1.0" standalone="yes"?>
<Paper uid="J88-3012">
  <Title>DISCOURSE MODELS~ DIALOG MEMORIES~ AND USER MODELS</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4 SEPARATING CRITERIA
</SectionTitle>
    <Paragraph position="0"> Previous attempts to separate user models from discourse models have used the short-time/long-time criterion, arguing that entries in the dialog memory can be forgotten after the end of the dialog, whereas entries in the user model are to be remembered. The same argument applies to dialog memories as part of the discourse model. The rationale of this argument is that anaphors are not applicable from one dialog to another and that the structure of a dialog is unlikely to be recalled as the syntactic structure of uttered sentences--just to mention these two phenomena.</Paragraph>
    <Paragraph position="1"> But does that mean that the entities with all their properties and relations as communicated in the dialog are forgotten? What would be the reason to talk to each other then? How could we learn from each other? Knowledge is to a great extent transferred via dialogs.</Paragraph>
    <Paragraph position="2"> Second, how could speech acts have social obligations as a consequence that may well hold for a long time? (Think of promises, for example!) Although the speaker may have forgotten the dialog, the hearer has--by very general conventions of language use--the right to insist on the speaker's commitments (Lewis 1975, Searle 1969, Wunderlich 1972).</Paragraph>
    <Paragraph position="3"> The synthesis of those seemingly conflicting observations is that the content of the dialog memory is integrated into the world knowledge. In other words, the conteilt of the focus space stack is partially incorporated into the world knowledge when it gets popped off the stack. So, the structure is lost, but the content is at least partly saved.</Paragraph>
    <Paragraph position="4"> Turniing things the other way around, why couldn't properties or character traits of a user be forgotten? What makes entries of a user model more stable? Think, for instance, of a post office clerk. Although he may adapt his behavior to the particular customer during the dialog, he normally forgets the information about her or him immediately after the dialog. As Rich (1979) pointed out, user models may be short term or long term. Thus short-time/long-time or forgettable/unforgettable is no criterion for dividing user models from dialog memories or discourse models.</Paragraph>
    <Paragraph position="5"> Another criterion could be, whether the knowledge is used for generating the linguistic form (how to say something) or for establishing the content of a system's utterance (what to say). Clearly, dialog memory and overall discourse model deal with the linguistic structure of dialogs, e.g., the reference resolution and the appropriate verbalization of concepts. The user model, on the other hand, also covers information that directs the selection of what to utter. The user's level of expertise determines the particularity of a system utterance, the realization of notes of caution, and the word choice, for instance. The user's wants establish the context of the user utterances and guide the system's problem solving, thus keeping the system behavior directed towards the user goals.</Paragraph>
    <Paragraph position="6"> This distinction, however, is not clear cut either, for two reasons. First, the line between what to say and how to say it is rather fuzzy. Referencing a concept, for example, also involves choosing the appropriate attributes for characterization--and this is naturally a matter of what to say. Second, this criterion would exclude work as presented by Lehman and Carbonell (1988) from the area of user modeling. There, linguistic rules are specialized for a particular user in a particular conversational setting. This is clearly not a matter of the dialog memory, but of the user model, although it is concerned with the linguistic form. Thus the form/ content distinction does not separate user models from dialog memories and discourse models, either.</Paragraph>
    <Paragraph position="7"> The difficulty to find criteria separating between discourse models and user models indicates a case of cross-classification. The criteria, namely what is specific to a user and what concerns dialog structure naturally cross. Dialog memory falls into both categories. null On the one hand, from what the user utters his beliefs, his level of expertise in a certain domain, his wants, and his language style can be inferred. This knowledge can be used by all the system components: tuning syntactic analysis, resolving reference, determining the input speech act, disambiguating the input, selecting relevant information, organizing the text to be 96 Computational Linguistics, Volume 14, Number 3, September 1988 Katharine Morik Discourse Models, Dialog Memories, and User Models outputted (Paris 1988), choosing the appropriate words, referencing, topicalizing, etc. In order to do so, all the components must include procedures that are parametrized according to the (particular) user model. Currently, the interactive systems do not put all the user facets to good use in all their components. This is not due to principled limits, however, but rather to a shortcoming in the state of the art.</Paragraph>
    <Paragraph position="8"> On the other hand, the user's utterances can also be analyzed from another viewpoint, namely incorporating them into a coherent discourse model as described by, e.g., Grosz and Sidner (1986). Also, this model can be used during all processing steps from understanding to generating.</Paragraph>
    <Paragraph position="9"> Both user models and discourse models are built up (at least partially) from the user utterances. Both contribute to a cooperative system behavior. But they do so from different viewpoints with different aims. Adopting to a particular user on the one hand and achieving a coherent, well-formed dialog on the other hand are two aims for a cooperative system which are orthogonal to each other. The terms user model and discourse model denote different aspects of a system. Thus although the notions are intensionally different, the extension of their respective definitions may overlap.</Paragraph>
  </Section>
class="xml-element"></Paper>