<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1097">
  <Title>Improving Automatic Indexing through Concept Combination and Term Enrichment</Title>
  <Section position="5" start_page="597" end_page="598" type="evalu">
    <SectionTitle>
4 Evaluation
</SectionTitle>
    <Paragraph position="0"> Qualitative evaluation: The volume of indexing is characterized by the surface of the text occupied by terms or their combinations-we call it the conceptual surface. Figure 2 shows the distribution of the sentences in relation to their conceptual surface. For instance, in 8,449 sentences among the 62,460 sentences of \[AGRIC\], the indexes occupy from 20 to 30% of the surface (3rd column).</Paragraph>
    <Paragraph position="1"> This figure indicates that the structures built from free indexing are significantly richer than those obtained from controlled indexing. The number of sentences is a decreasing exponential function of their conceptual surface (a linear function with a log scale on the y axis).</Paragraph>
    <Paragraph position="2"> Figure 3 illustrates how the successive steps of the algorithm contribute to the final size of the incremental indexing. For each mode of  indexing two curves are plotted: the phrases resulting from initial indexing and from reindexing due to text condensation (circles) and the phrases due to term acquisition (asterisks). For instance, at step3, free indexing yields 309 indexes and reindexing 645. The corresponding percentages are reported in Table 2.</Paragraph>
    <Paragraph position="3"> The indexing with the poorest initial volume (controlled indexing) is the one that benefits best from term acquisition. Thus, concept combination and term enrichment tend to compensate the deficiencies of the initial term list by extracting more knowledge from the corpus.</Paragraph>
    <Paragraph position="4"> 10 5, &amp;quot;~ 10 4.</Paragraph>
    <Paragraph position="5">  Qualitative evaluation: Table 3 indicates the number of overlapping indexes in relation to their type. It provides, for each type, the rate of success of the structuring algorithm. This eva- null luation results from a human scanning of 542 randomly chosen structures.</Paragraph>
  </Section>
class="xml-element"></Paper>