<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1036">
  <Title>Unsupervised Segmentation of Words Using Prior Distributions of Morph Length and Frequency</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> The results we have obtained suggest that the performance of a segmentation algorithm can indeed be increased by using prior information of general nature, when this information is expressed mathematically as part of a probabilistic model. Furthermore, we have reasons to believe that the morph segments obtained can be useful as components of a statistical language model.</Paragraph>
  </Section>
class="xml-element"></Paper>