<?xml version="1.0" standalone="yes"?>
<Paper uid="A92-1002">
  <Title>A Dialog Control Algorithm and Its Performance</Title>
  <Section position="9" start_page="14" end_page="14" type="concl">
    <SectionTitle>
7 Summary
</SectionTitle>
    <Paragraph position="0"> A voice interactive dialog architecture has been developed which achieves simultaneously a variety of behaviors believed to be necessary for efficient human-machine dialog. Goal oriented behavior is supplied by the theorem proving paradigm. Subdialogs and movement between them is implemented with an interruptible theorem prover that maintains a set of partially completed proofs and can work on the most appropriate one at any given time. A user model is provided by a continuously changing set of rules that are referenced in the theorem proving process either to enable or inhibit voice dialog. Mixed initiative is made possible by variable types of processing by the output and input routines and by restricting or releasing the ability to interrupt to a new subdialog. Expectation is associated with individual subdialogs, is compiled from domain and dialog information related to each specific output, and is used to improve voice recognition and enable movement between subdialogs.</Paragraph>
    <Paragraph position="1"> ~Of the 23 dialogs which were not completed, 22 were terminated prematurely due to excessive time being spent on the dialog. Misunderstandings due to misrecognition were the cause in 13 of these failures. Misunderstandings due to inadequate grammar coverage occurred in 3 of the failures.</Paragraph>
    <Paragraph position="2"> In 4 of the failures the subject misconnected a wire. In one failure there was confusion by the subject about when the circuit was working, and in another failure there were problems with the system software. A hardware failure caused termination of the final dialog.</Paragraph>
  </Section>
class="xml-element"></Paper>