<?xml version="1.0" standalone="yes"?>
<Paper uid="P96-1025">
  <Title>A New Statistical Parser Based on Bigram Lexical Dependencies</Title>
  <Section position="7" start_page="190" end_page="190" type="concl">
    <SectionTitle>
5 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have shown that a simple statistical model based on dependencies between words can parse Wall Street Journal news text with high accuracy.</Paragraph>
    <Paragraph position="1"> The method is equally applicable to tree or dependency representations of syntactic structures.</Paragraph>
    <Paragraph position="2"> There are many possibilities for improvement, which is encouraging. More sophisticated estimation techniques such as deleted interpolation should be tried. Estimates based on relaxing the distance measure could also be used for smoothing- at present we only back-off on words. The distance measure could be extended to capture more context, such as other words or tags in the sentence. Finally, the model makes no account of valency.</Paragraph>
  </Section>
class="xml-element"></Paper>