<?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="4" start_page="0" end_page="223" type="intro">
    <SectionTitle>
2 Motivation
</SectionTitle>
    <Paragraph position="0"> PP attachment disambiguation has often been studied as a benchmark test for empirical methods in natural language processing. Prepositions allow subordination to many different attachment sites, and the choice between them is influenced by factors from many different linguistic levels, which are generally subject to preferential rather than rigorous regularities. For this reason, PP attachment is a comparatively difficult subtask for rule-based syntax analysis and has often been attacked by statistical methods.</Paragraph>
    <Paragraph position="1"> Because probabilistic approaches solve PP attachment as a natural subtask of parsing anyhow, the obvious application of a PP attacher is to integrate it into a rule-based system. Perhaps surprisingly, so far this has rarely been done. One reason for this is that many rule-driven syntax analyzers provide no obvious way to integrate uncertain, statistical information into their decisions. Another is the traditional emphasis on PP attachment as a binary classification task; since (Hindle and Rooth, 1991), research has concentrated on resolving the ambiguity in the category pattern 'V+N+P+N', i.e. predicting the PP attachment to either the verb or the first noun. It is often assumed that the correct attachment is always among these  two options, so that all problem instances can be solved correctly despite the simplification. This task is sufficient to measure the relative quality of different probability models, but it is quite different from what a parser must actually do: It is easier because the set of possible answers is pre-filtered so that only a binary decision remains, and the baseline performance for pure guessing is already 50%. But it is harder because it does not provide the predictor with all the information needed to solve many doubtful cases; (Hindle and Rooth, 1991) found that human arbiters consistently reach a higher agreement when they are given the entire sentence rather than just the four words concerned.</Paragraph>
    <Paragraph position="2"> Instead of the accuracy of PP attachers in the isolated decision between two words, we investigate the problem of situated PP attachment. In this task, all nouns and verbs in a sentence are potential attachment points for a preposition; the computer must find suitable attachments for one or more prepositions in parallel, while building a globally coherent syntax structure at the same time.</Paragraph>
  </Section>
class="xml-element"></Paper>