<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1081">
  <Title>Chinese Segmentation and New Word Detection using Conditional Random Fields</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> The contribution of this paper is three-fold. First, we apply CRFs to Chinese word segmentation and find that they achieve state-of-the art performance.</Paragraph>
    <Paragraph position="1"> Second, we propose a probabilistic new word detection method that is integrated in segmentation, and show it to improve segmentation performance.</Paragraph>
    <Paragraph position="2"> Third, as far as we are aware, this is the first work to comprehensively evaluate on the four benchmark datasets, making a solid baseline for future research on Chinese word segmentation.</Paragraph>
  </Section>
class="xml-element"></Paper>