<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1664">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Graph-based Word Clustering using a Web Search Engine</Title>
  <Section position="7" start_page="548" end_page="548" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper describes a new approach for word clustering using a search engine. The chi-square measure is used to overcome the broad range of word counts for a given set of words. We also apply recently-developed Newman clustering, which yields promising results through our evaluations.</Paragraph>
    <Paragraph position="1"> Our algorithm has few parameters. Therefore, it can be used easily as a baseline, as suggested by (Lapata and Keller, 2004). New words are generated day by day on the web. We believe that to automatically identify new words and obtain word groups potentially enhances many NLP applications. null</Paragraph>
  </Section>
class="xml-element"></Paper>