<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3810">
  <Title>Graph-based Generalized Latent Semantic Analysis for Document Representation</Title>
  <Section position="5" start_page="63" end_page="63" type="concl">
    <SectionTitle>
4 Conclusion and Future Work
</SectionTitle>
    <Paragraph position="0"> We introduced a graph-based method of dimensionality reduction into the GLSA framework. Laplacian Eigenmaps Embedding preserves the similarities only locally, thus providing a potentially better approximation to the low dimensional semantic space. We explored the role of locality in the GLSA representation and used binary adjacency matrix as similarity which was preserved and compared it to GLSA with unnormalized PMI scores.</Paragraph>
    <Paragraph position="1"> Our results did not show an advantage of GLSAL.</Paragraph>
    <Paragraph position="2"> GLSAL and LPI seem to be very sensitive to the parameters of the neighborhood graph. We tried different parameter settings but more experiments are required for a thorough analysis. We are also planning to use a different document collection to eliminate the possible effect of the specific term distribution in the Reuters collection. Further experiments are needed to make conclusions about the geometry of the vocabulary space and the appropriateness of these methods for term and document embedding.</Paragraph>
  </Section>
class="xml-element"></Paper>