<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1117">
  <Title>A Maximum-Entropy Partial Parser for Unrestricted Text</Title>
  <Section position="8" start_page="148" end_page="148" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have demonstrated a partial parser capable of recognising simple and complex NPs, PPs and APs in unrestricted German text.</Paragraph>
    <Paragraph position="1"> The maximum entropy parameter estimation method allows us to optimally use the context information contained in the training sample. On the other hand, the parser can still be viewed as a Markov model, which guarantees high efficiency (processing in linear time). The program can be trained even with a relatively small amount of treebank data; then it can be J used for parsing unrestricted pre-tagged text.</Paragraph>
    <Paragraph position="2"> As far as coverage is concerned, our parser can handle recursive structures, which is an advantage compared to simpler techniques such as that described by Church (1988). On the other hand, the Markov assumption underlying our approach means that only strictly local dependencies are recognised. For full parsing, one would probably need non-local contextual information, such as the long-range trigrams in Link Grammar (Della Pietra et al., 1994).</Paragraph>
    <Paragraph position="3"> Our future research will focus on exploiting morphological and lexical knowledge for partial parsing. Lexical context is particularly relevant for the recognition of genitive NP and PP attachment, as well as complex proper names. We hope that our approach will benefit from related work on this subject, cf. (Ratnaparkhi et al., 1994). Further precision gain can also be achieved by enriching the structural context, e.g. with information about the category of the grandparent node.</Paragraph>
  </Section>
class="xml-element"></Paper>