<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-2049">
  <Title>Dependency Analyzer: A Knowledge-Based Approach to Structural Disambiguation</Title>
  <Section position="2" start_page="0" end_page="282" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The bottleneck of sentence analysis, structural ambiguity, occurs when a sentence has several alternatives for modifier-modifiee relationships (dependencies) between words or phrases. This kind of ambiguity cannot be resolved merely by applying grammatical knowledge: there is a need for semantic processing. Resolution of structural ambiguities seems to be a problem of selecting the most preferable dependency from several candidates by using large-scale knowledge on dependencies among words.</Paragraph>
    <Paragraph position="1"> There are two problems in realizing practical semantic processing: one is that knowledge must be large-scale, and must be constructed automatically or semi-automatically; the other is that the mechanism for utilizing knowledge, inference, must be efficient or tractable. We developed a system called the Dependency Analyzer that resolves these problems.</Paragraph>
    <Paragraph position="2"> The Dependency Analyzer is a systenl fl)r structural disambignation. One of its characteristics is that it selects the most preferabledependency by using a knowledge base containing terminological knowledge in the form of dependency trees. The knowledge base can be constructed semiautomatically, as described in Section 2. The inputs of this system are parse trees, which are outputs of the PEG parser, a broad coverage English parser \[5\]. The system translates the phrase structures into dependency strut- null tures that explicitly represent modifier-modifiee relationships between words. The main processes of the system are executed if attachment ambiguities are included in the phrase structures. In the dependency structures, attachment ambiguities are represented by showing that some words have several candidate modiliees. From these depe.ndency structures, several candidate dependencies are extracted. The system decides which of these should be adopted by using background knowledge an,l context. The decision is made via tim mechanisms of path search and distance calculation. A precise description of path search is given in Section 3. An explanation of distance calculation is given in Section 4. Another problem for disambiguation, namely interaction (or constraints) between attachment ambiguities, is discussed in Section 5.</Paragraph>
  </Section>
class="xml-element"></Paper>