<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2929">
  <Title>Vine Parsing and Minimum Risk Reranking for Speed and Precision[?]</Title>
  <Section position="10" start_page="204" end_page="204" type="concl">
    <SectionTitle>
8 Conclusion
</SectionTitle>
    <Paragraph position="0"> The tradeoff between speed and accuracy is familiar to any parsing researcher. Rather than starting with an accurate system and then applying corpus-specific speedups, we start by imposing carefullychosen constraints (projectivity and length bounds) for speed, leaving accuracy to the parsing and reranking models. As it stands, our system performs poorly, largely because the estimation is not stateof-the-art, but also in part due to dependency length bounds, which are rather coarse at present. Better results are achievable by picking different bounds for different head tags (Eisner and N. Smith, 2005). Accuracy should not be difficult to improve using better learning methods, especially given our models' linear-time inference and decoding.</Paragraph>
  </Section>
class="xml-element"></Paper>