File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/98/w98-1410_concl.xml

Size: 2,121 bytes

Last Modified: 2025-10-06 13:58:21

<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1410">
  <Title>Macroplanning with a Cognitive Architecture for the Adaptive Explanation of Proofs</Title>
  <Section position="6" start_page="93" end_page="93" type="concl">
    <SectionTitle>
5 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> in this paper, we proposed to combine thetraditional design of a dialog planner with a cognitive architecture in order to strive for an optimal user adaptation. In the interactive proof explaining system P. rex, the dialog planner is based on the theory of cognition AcT-R.</Paragraph>
    <Paragraph position="1"> Starting from certain assumptions about the addressee's knowledge (e.g. which facts does he know, which definitions, lemmasl etc.) built up in the user model during previous sessions, the dialog planner decides on which level of abstraction* to begin the explanation. Since AcT-R traces the user's Cognitive states during the explanation, the dialog planner can choose an appropriate degree of abstraction for each proof step to be explained. The rationale behind this architecture should prove to be useful for explanation systems in general.</Paragraph>
    <Paragraph position="2"> Moreover since this architecture can predict what is salient for the user and what he can infer, it could be used as a basis to decide whether or not to include optional information \[Walker and Rambow, 1994\].</Paragraph>
    <Paragraph position="3"> P. rex is still in the design stage. As soon as the dialog planner is implemented the requirements will be met to compare P. rex's dialog plans with PROVERB's text plans in order to evaluate the architecture. Furthermore ' the presentation component and the analyzer are to be designed in more *detail.</Paragraph>
    <Paragraph position="4"> Currently, we are examining the knowledge compilation mechanism of AcT-R that Could enable the system to model the user's acquisition of proving skills. This could pave the way towards a tutorial system that not only explains )roofs, but also teaches concepts and proving methods and strategies.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML