<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1654">
  <Title>Random Indexing using Statistical Weight Functions</Title>
  <Section position="10" start_page="462" end_page="463" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have applied weighting functions to the vector space approximation Random Indexing. For large data sets we found a significant improvement  when weights were applied. For smaller data sets we found that Random Indexing was sufficiently robust that weighting had at most a minor effect. Our weighting schemes removed the possibility of incremental learning of the term space. An interesting direction would be the development of algorithms that allowed the incremental application of weights, perhaps by re-weighting vectors when a new context is learned.</Paragraph>
    <Paragraph position="1"> Other areas left open for investigation are the interaction between Random Indexing, weights and the type of context extracted, the use of large-scale bilingual corpora, the acquisition of lexicons for non-Indo-European languages and across language family boundaries, and the difference in effect term and paragraph/document contexts for thesaurus extraction.</Paragraph>
    <Paragraph position="2"> We have demonstrated that the accuracy of Random Indexing can be improved by applying weight functions, increasing accuracy by up to 50% on the BNC and 100% on a 2 billion word corpus.</Paragraph>
  </Section>
class="xml-element"></Paper>