<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2243">
  <Title>How to thematically segment texts by using lexical cohesion?</Title>
  <Section position="5" start_page="1482" end_page="1482" type="concl">
    <SectionTitle>
4 Conclusion and future work
</SectionTitle>
    <Paragraph position="0"> We have presented a method for segmenting texts into thematically coherent units that relies on a collocation network. This collocation network is used to compute a cohesion value for the different parts of a text. Segmentation is then done by analyzing the resulting cohesion graph. But such a numerical value is a rough characterization of the current topic.</Paragraph>
    <Paragraph position="1"> For future work we will build a more precise representation of the current topic based on the words selected from the network. By computing a similarity measure between the representation of the current topic at one position of the window and this representation at a further one, it will be possible to determine how thematically far two parts of a text are. The minima of the measure will be used to detect the thematic shifts. This new method is closer to Hearst's than the one presented above but it relies on a collocation network for finding relations between two parts of a text instead of using the word recurrence.</Paragraph>
  </Section>
class="xml-element"></Paper>