<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1212">
  <Title>I l I I | l / A Bayesian Approach to Automating Argumentation</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> NAG uses a series of focusing-generation-analysis cycles to build two Bayesian networks (one in the normative model and another in the user model) that contain the information required to construct a nice argument. Partial propagation, performed over the subnetworks in focus (the current Argument Graph), is used to estimate the impact of the resultant argument. Modified Bayesian update rules model three human cognitive weaknesses.</Paragraph>
    <Paragraph position="1"> Any argumentation system must have access to a great deal of domain specific data if it is to generate and analyze arguments well. NAG is no exception, and consequently setting up a good domain, one with sufficient depth and richness to test NAG well, is not trivial. By allowing NAG to use existing knowledge sources where possible, via small Reasoning Agents written to match the various knowledge source types, we have endeavoured to at least partially mitigate this problem.</Paragraph>
    <Paragraph position="2"> NAG has been tested on five sample scenarios which generate BNs containing up to about 50 nodes. The use of spreading activation to simulate attention, and the simplifications NAG employs to reduce the time taken to extend and propagate beliefs through the Bayesian subnetworks, lead to a significant reduction in argument generation times compared to trials run with the same BNs not using these techniques. These speed-up methods seem to have little effect on the resulting arguments.</Paragraph>
    <Paragraph position="3"> Larger BNs and KBs, which are currently being built, will enable us to test more conclusively the effects of our modifications on the speed of the generation process and the quality of the arguments produced. These richer scenarios will also allow us to better test the effects of our modeling of human cognitive weaknesses. We are currently planning a variety of tests to evaluate the performance of our system. The graphical interface currently under construction and an English generator will be used to test the effect of arguments generated by NAG on users' beliefs. In addition, the English output will be used to compare NAG's arguments with those generated by people and to test how the order of presentation of the points in an argument affects users' beliefs.</Paragraph>
  </Section>
class="xml-element"></Paper>