<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1320">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics An Analysis of Quantitative Aspects in the Evaluation of Thematic Segmentation Algorithms</Title>
  <Section position="10" start_page="149" end_page="149" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> By comparing the performance of three systems for thematic segmentation on different kinds of data, we address two important issues in a quantitative evaluation. Strong emphasis was put on the kind of data used for evaluation and we have demonstrated experimentally that evaluation on synthetic data is potentially misleading. The second major issue addressed in this paper concerns the choice of a valuable error metric and its side effects on the evaluation assessment.</Paragraph>
  </Section>
class="xml-element"></Paper>