<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1054">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Fast, Accurate Deterministic Parser for Chinese</Title>
  <Section position="11" start_page="430" end_page="431" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we presented a novel deterministic parser for Chinese constituent parsing. Using gold-standard POS tags, our best model (using stacked classifiers) runs in linear time and has labeled recall and precision of 88.3% and 88.1%, respectively, surpassing the best published results.</Paragraph>
    <Paragraph position="1"> And with a trade-off of 5-6% in accuracy, our DTree and Maxent parsers run at speeds 40-270 times faster than state-of-the-art parsers. Our re- null sults have shown that the deterministic parsing framework is a viable and effective approach to Chinese parsing. For future work, we will further improve the speed and accuracy of our models, and apply them to more Chinese and multi-lingual natural language applications that require high speed and accurate parsing.</Paragraph>
  </Section>
class="xml-element"></Paper>