<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0709">
  <Title>The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution</Title>
  <Section position="9" start_page="68" end_page="69" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we present a fully fledged Entity Detection and Tracking system for Arabic. At its base, the system fundamentally depends on a finite state segmenter and makes good use of the relationships that occur between word stems, by introducing features which take into account the type of each segment.</Paragraph>
    <Paragraph position="1"> In mention detection, the features are represented as stem n-grams, while in coreference resolution they are captured through stem-tailored match features.</Paragraph>
    <Paragraph position="2">  erence resolution. The row marked with &amp;quot;Truth&amp;quot; represents the results with &amp;quot;true&amp;quot; mentions while the row marked with &amp;quot;System&amp;quot; represents that mentions are detected by the system. Numbers under &amp;quot;ECM-F&amp;quot; are Entity-Constrained-Mention F-measure and numbers under &amp;quot;ACE-Val&amp;quot; are ACE-values.</Paragraph>
    <Paragraph position="3"> These types of features result in an improvement in both the mention detection and coreference resolution performance, as shown through experiments on the ACE 2004 Arabic data. The experiments are performed on a clearly specified partition of the data, so comparisons against the presented work can be correctly and accurately made in the future. In addition, we also report results on the official test data. The presented system has obtained competitive results in the ACE 2004 evaluation, being ranked amongst the top competitors.</Paragraph>
  </Section>
class="xml-element"></Paper>