<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1704">
  <Title>CUCWeb: a Catalan corpus built from the Web</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper presents CUCWeb, a 166 million word corpus for Catalan built by crawling the Web. The corpus has been annotated with NLP tools and made available to language users through a flexible web interface. The developed architecture is quite general, so that it can be used to create corpora for other languages.</Paragraph>
  </Section>
class="xml-element"></Paper>