<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2029">
  <Title>The Benefit of Stochastic PP Attachment to a Rule-Based Parser</Title>
  <Section position="7" start_page="227" end_page="228" type="relat">
    <SectionTitle>
5 Related Work
</SectionTitle>
    <Paragraph position="0"> (Hindle and Rooth, 1991) first proposed solving the prepositional attachment task with the help of statistical information, and also defined the prevalent formulation as a binary decision problem with three words involved. (Ratnaparkhi et al., 1994)  extended the problem instances to quadruples by also considering the kernel noun of the PP, and used maximum entropy models to estimate the preferences.</Paragraph>
    <Paragraph position="1"> Both supervised and unsupervised training procedures for PP attachment have been investigated and compared in a number of studies, with supervised methods usually being slightly superior (Ratnaparkhi, 1998; Pantel and Lin, 2000), with the notable exception of (Volk, 2002), who obtained a worse accuracy in the supervised case, obviously caused by the limited size of the available treebank. Combining both methods can lead to a further improvement (Volk, 2002; Kokkinakis, 2000), a finding confirmed by our experiments.</Paragraph>
    <Paragraph position="2"> Supervised training methods already applied to PP attachment range from stochastic maximum likelihood (Collins and Brooks, 1995) or maximum entropy models (Ratnaparkhi et al., 1994) to the induction of transformation rules (Brill and Resnik, 1994), decision trees (Stetina and Nagao, 1997) and connectionist models (Sopena et al., 1998). The state-of-the-art is set by (Stetina and Nagao, 1997) who generalize corpus observations to semantically similar words as they can be derived from the WordNet hierarchy.</Paragraph>
    <Paragraph position="3"> The best result for German achieved so far is the accuracy of 80.89% obtained by (Volk, 2002).</Paragraph>
    <Paragraph position="4"> Note, however, that our goal was not to optimize the performance of PP attachment in isolation but to quantify the contribution it can make to the performance of a full parser for unrestricted text. The accuracy of PP attachment has rarely been evaluated as a subtask of full parsing. (Merlo et al., 1997) evaluate the attachment of multiple prepositions in the same sentence for English; 85.3% accuracy is achieved for the first PP, 69.6% for the second and 43.6% for the third. This is still rather different from our setup, where PP attachment is fully integrated into the parsing problem. Closer to our evaluation scenario comes (Collins, 1999) who reports 82.3%/81.51% recall/precision on PP modifications for his lexicalized stochastic parser of English. However, no analysis has been carried out to determine which model components contributed to this result.</Paragraph>
    <Paragraph position="5"> A more application-oriented view has been adopted by (Schwartz et al., 2003), who devised an unsupervised method to extract positive and negative lexical evidence for attachment preferences in English from a bilingual, aligned English-Japanese corpus. They used this information to re-attach PPs in a machine translation system, reporting an improvement in translation quality when translating into Japanese (where PP attachment is not ambiguous and therefore matters) and a decrease when translating into Spanish (where attachment ambiguities are close to the original ones and therefore need not be resolved).</Paragraph>
    <Paragraph position="6"> Parsing results for German have been published a number of times. Combining treebank transformation techniques with a suffix analysis, (Dubey, 2005) trained a probabilistic parser and reached a labelled F-score of 76.3% on phrase structure annotations for a subset of the sentences used here (with a maximum length of 40). For dependency parsing a labelled accuracy of 87.34% and an unlabelled one of 90.38% has been achieved by applying the dependency parser described in (Mc-Donald et al., 2005) to German data. This system is based on a procedure for online large margin learning and considers a huge number of locally available features, which allows it to determine the optimal attachment fully deterministically. Using a stochastic variant of Constraint Dependency Grammar (Wang and Harper, 2004) reached a 92.4% labelled F-score on the Penn Treebank, which slightly outperforms (Collins, 1999) who reports 92.0% on dependency structures automatically derived from phrase structure results.</Paragraph>
  </Section>
class="xml-element"></Paper>