<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0104">
  <Title>II I A Statistics-Based Chinese Parser</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> This paper describes a statistics-based Chinese parser, which parses the Chinese sentences with correct segmentation and POS tagging information through the following processing stages: 1) to predict constituent boundaries, 2) to match open and close brackets and produce syntactic trees, 3) to disambiguate and choose the best parse tree. Evaluating the parser against a smaller Chinese treebank with 5573 sentences, it shows the following encouraging results: 86% precision, 86% recall, 1.1 crossing brackets per sentence and 95% labeled precision.</Paragraph>
  </Section>
class="xml-element"></Paper>