<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1220">
  <Title>I Evolution and Evaluation of Document Retrieval Queries</Title>
  <Section position="5" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5. Conclusion
</SectionTitle>
    <Paragraph position="0"> This abstract describes the starting point of a project we are undertaking on the evolution of useful rules for search enhancement. There are a number of probable advantages to using the approach given above, to produce a search enhancer. Firstly, the use of Genetic Programming allows the discovery of optimal search expressions that would not necessarily be intuitively chosen. Secondly, the query expansion methods produced will be general, so that they can be utilized in any particular query made, and thereby much increases the general usefulness of the system. Thirdly, the system does not assume improvements in the underlying search engine technology and so is more easily applied.</Paragraph>
    <Paragraph position="1"> Although the present query expansion method is static - that is, evolution stops on delivery due to the cost of on-line evolution, we are also developing low cost ideas for continuing the evolution using cache information, pre-fetch and post-fetch, thereby allowing dynamic user profiling.</Paragraph>
  </Section>
class="xml-element"></Paper>