<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-3022">
  <Title>Chinese Word Segmentation in FTRD Beijing</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The development of the Chinese word segmentation system presented in this bakeoff began in Feb. this year, and will last for one year with the support of the ILAB Beijing initial project within France Telecom R&amp;D.</Paragraph>
    <Paragraph position="1"> Although the project last only half year by now, the main components of the system has been implemented, including code identification and conversion, basic segmentation, factoid detection, morphological analysis, name entity identification, segmentation standards adaptor, except the components of code identification and conversion and segmentation standards adaptors, other components are integrated in a statistical framework of n-gram language model.</Paragraph>
  </Section>
class="xml-element"></Paper>