<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1043">
  <Title>A language-independent shallow-parser Compiler</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> We present a rule-based shallow-parser compiler, which allows to generate a robust shallow-parser for any language, even in the absence of training data, by resorting to a very limited number of rules which aim at identifying constituent boundaries.</Paragraph>
    <Paragraph position="1"> We contrast our approach to other approaches used for shallow-parsing (i.e. finite-state and probabilistic methods). We present an evaluation of our tool for English (Penn Treebank) and for French (newspaper corpus &amp;quot;LeMonde&amp;quot;) for several tasks (NP-chunking &amp; &amp;quot;deeper&amp;quot; parsing) .</Paragraph>
  </Section>
class="xml-element"></Paper>