<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1052">
  <Title>Modifying Beliefs in a Plan-Based Dialogue Model</Title>
  <Section position="2" start_page="0" end_page="349" type="metho">
    <SectionTitle>
2 Plans, Beliefs, and Processing
</SectionTitle>
    <Paragraph position="0"> My plan-based model of dialogue incrementally builds a structure of the discourse (a Dialogue Model, or DM) using a multi-level belief model updated after each utterance. The belief model contains the beliefs ascribed to the user during the course of the conversation and how strongly each belief is held.</Paragraph>
    <Paragraph position="1"> Researchers \[1, 3, 5\] have noted that discourse understanding can be enhanced by recognizing a user's goals, and that this recognition process requires reasoning about the agent's beliefs \[7\]. For example, in order to recognize from utterance IS2 in the following dialogue that the speaker has the communicative goal of expressing surprise at the proposition that Dr. Smith is teaching CIS360 and not just asking if Dr. Smith is teaching CIS420, it is necessary for the system to be able to plausibly ascribe to IS the beliefs that 1) Dr.</Paragraph>
    <Paragraph position="2"> Smith is teaching CIS420; 2) that this somehow implies that Dr. Smith is not teaching CIS360; and 3) that IP believes that Dr. Smith is teaching CIS360.</Paragraph>
    <Paragraph position="3"> ISI: Who is teaching CIS 360? IPl: Dr. Smith.</Paragraph>
    <Paragraph position="4"> IS2: Dr. Smith is teaching CIS 420, isn't she? IP2: Yes, she is. Dr. Smith is teaching two courses.</Paragraph>
    <Paragraph position="5"> IS3: What time is CIS 360? My model ascribes these beliefs to IS as the discourse proceeds, anti uses the ascribed beliefs for recognizing utterances that involve negotiation dialogues. Without the ability to modify a belief model as a dialogue progresses, it would not be possible to plausibly ascribe 1) or 3), so it is unclear how recognizing expressions of surprise would be accomplished in systems such as Litman's \[5\] that recognize discourse goals but do not maintain belief models. IS2 also exemplifies how people may have levels of belief and indicate those levels in the This material is based upon work supported by the National Science Foundation under Grant No. IRI-8909332. The Government has certain rights in this material.</Paragraph>
    <Paragraph position="6"> surface form of utterances. Here, IS uses a tag question to indicate that he thinks that Dr. Smith is teaching CIS420, but is not certain of it. My belief model maintains three levels of belief, three levels of disbelief, and one level indicating no belief about a proposition.</Paragraph>
    <Paragraph position="7"> My process model begins with the semantic representation of an utterance. The effects of the surface speech act, such as a tag question, are used to suggest augmentations to the belief model. Plan inference rules are used to infer actions that might motivate the utterance; the belief ascription process during constraint satisfaction determines whether it is reasonable to ascribe the requisite beliefs to the agent of the action and, if not, the inference is rejected. Focusing heuristics allow expectations derived from the existing dialogue context to guide the recognition process by preferring those inferences that lead to the most coherent expansions of the existing dialogue model.</Paragraph>
    <Paragraph position="8"> The resultant DM contains a structure of the dialogue at every point in the discourse, including three different kinds of goals, each modeled on a separate level: the domain level models domain goals such as traveling by train; the problem-solving level, plan-construction goals such as instantiating a variable in a plan; and the discourse level, communicative goals such as express.</Paragraph>
    <Paragraph position="9"> ing surprise. Within each of these levels, actions may contribute to other actions on the same level; for example, on the discourse level, providing background data, asking a question, and answering a question all can be part of obtaining information. 2 So, actions at each level form a tree structure in which each node represents an action that a participant is performing and the children of a node represent actions pursued in order to perform the parent action. This tree structure allows my model to capture the relationship among several utterances that are all part of the same higher-level discourse plan, which is not possible in Litman's model \[5\]. In addition, an action on one level may contribute to, or link to, an action on an immediately higher level.</Paragraph>
    <Paragraph position="10"> For example, discourse actions may be executed to attain the knowledge needed for problem-solving actions at the middle level.</Paragraph>
    <Paragraph position="11"> This tripartite, plan-based model of discourse fa- null plicitly captures a number of intentions that are attributed to the participants, such as the intention that the participants follow through with the subactions that are part of plans for actions in the DM.</Paragraph>
    <Paragraph position="12">  cilitates recognition of changing beliefs as the dialogue progresses. Allen's representation of an Inform speech act \[1\] assumed that a listener adopted the communicated proposition. Clearly, listeners do not adopt everything they are told (e.g., IS2 indicates that IS does not immediately accept that Dr. Smith is teaching CIS360).</Paragraph>
    <Paragraph position="13"> Perrault \[6\] assumed that a listener adopted the communicated proposition unless the listener had conflicting beliefs, as in IS2. Unfortunately, Perrault assumes that people's beliefs persist so it would not be possible for Perranlt to model IS adopting IP's explanation in IP2. I am assuming that the participants are involved in a cooperative dialogue, so try to square away their beliefs \[4\]. Thus, after every Inform action, a speaker expects the listener either to accept any claims that the speaker made or to initiate a negotiation dialogue. 3 Acceptance can be communicated in two ways. Either the listener can explicitly indicate acceptance (e.g., &amp;quot;oh, alright&amp;quot;), or the listener can implicitly convey acceptance \[2\] by making an utterance which cannot be interpreted as initiating a negotiation dialogue. Since both parties are engaged in a cooperative dialogue in which beliefs are squared away, this failure to initiate a negotiation dialogue by default indicates (implicit) acceptance of any claims not disputed. This corresponds with a restricted form of Perrault's default reasoning about the effects of Inform acts \[6\]. An example of implicit acceptance is considered in the next section.</Paragraph>
  </Section>
  <Section position="3" start_page="349" end_page="349" type="metho">
    <SectionTitle>
3 Example
</SectionTitle>
    <Paragraph position="0"> Consider the dialogue model given in Section 2.</Paragraph>
    <Paragraph position="1"> The process model infers from the first utterance that IS is executing a high level discourse action of Obtain.Info-Ref to determine who is teaching CIS360 and problem-solving actions of Insfanfiate- Var and Build-Plan in order to build a plan to take CIS360 so that IS may eventually execute a domain action, Take-Course, to take CIS360. IS2 is recognized as an expression of surprise at IP's answer since acceptance or negotiation of the answer is expected and since the following beliefs can be ascribed to IS: 1) as a default rule, that teachers generally teach only one course; 2) that Dr. Smith is already teaching CIS420 (from the tag question form); and 3) that the combination of 1) and 2) implies that Dr. Smith is not teaching CIS360. IP responds by trying to make her answer believable and to resolve the conflict. This is done by informing IS that his belief about Dr. Smith teaching CIS420 is correct, but that Dr. Smith is an exception to the default rule.</Paragraph>
    <Paragraph position="2"> Focusing heuristics suggest explicit acceptance of or objection to IP~ as ways to continue the current discourse plan. However utterance IS3, instead, pursues a 3A third possibility exists: that the participants agree to disagree about a particular point, and continue the dialogue. My model will handle this also, but it is not preferred, and for space reasons will not be considered further here.</Paragraph>
    <Paragraph position="3"> completely new discourse action, Obtain-Info-Ref, unrelated to the original Obtain-Info-Ref, though still related to the problem-solving action of Instantiate-Var in order to build a plan to take CIS360. Since a new discourse plan is being pursued, the process model infers by default that IP2 has been accepted because otherwise IS would have initiated a negotiation dialogue.</Paragraph>
    <Paragraph position="4"> Since the inform action is accepted (implicitly), this action, and the higher level actions that it contributes to, are considered to be successfully completed, so the goals and effects of these plans are considered to hold. Some of the goals of these plans are that 1) IS believes that Dr. Smith teaches both CIS360 and CIS420, and thus is an exception to the default rule that teachers only teach one course and 2) IS knows that Dr. Smith is the faculty member that teaches CIS360, the answer to the original question that IS asked. Once the process model recognizes IS3 as pursuing this new Obtain-Info-Ref action, the belief model is updated accordingly.</Paragraph>
  </Section>
class="xml-element"></Paper>