<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1509">
  <Title>Lexical and Structural Biases for Function Parsing</Title>
  <Section position="7" start_page="90" end_page="90" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper, we have explored a new way to improve parsing results in a current statistical parser while at the same time enriching its output. We achieve significant improvements in parsing and function labelling by modelling directly the specific nature of function labels, as both expressions of the lexical semantics properties of a constituent and as syntactic elements whose distribution is subject to structural locality constraints. Differently from other approaches, the method we adopt integrates function labelling directly in the parsing process.</Paragraph>
    <Paragraph position="1"> Future work will lie in exploring new ways of capturing syntactic domains, different from the ones attempted in the current paper, such as developing new derivation moves for nodes bearing function labels.</Paragraph>
    <Paragraph position="2"> A more detailed analysis of the parser will also shed light on its behaviour on sequences of function labels. Finally, we plan to extend this work to learn Propbank-style semantic role labels, which might require explicit modelling of long distance dependencies and syntactic movement.</Paragraph>
  </Section>
class="xml-element"></Paper>