<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1015">
  <Title>Semi-Automatic Recognition of Noun Modifier Relationships</Title>
  <Section position="3" start_page="0" end_page="96" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="96" type="sub_section">
      <SectionTitle>
2.1 Noun Compounds
</SectionTitle>
      <Paragraph position="0"> A head noun along with a noun premodifier is often called a noun compound. Syntactically a noun compound acts as a noun: a modifier or a head may again be a compound. The NMR analyzer deals with the semantics of a particular kind of compound, namely those that are transparent and endocentric.</Paragraph>
      <Paragraph position="1"> The meaning of a transparent compound can be derived from the meaning of its elements. For example, laser printer is transparent (a printer that uses a laser). Guinea pig is opaque: there is no obvious direct relationship to guinea or to pig. An endocentric compound is a hyponym of its head. Desktop computer is endocentric because it is a kind of computer. Bird brain is exocentric because it does not refer to a kind of brain, but rather to a kind of person (whose brain resembles that of a bird).</Paragraph>
      <Paragraph position="2"> Since the NMR analyzer is intended for technical texts, the restriction to transparent endocentric compounds should not limit the utility of the system. Our experiments have found no opaque or exocentric compounds in the test texts.</Paragraph>
    </Section>
    <Section position="2" start_page="96" end_page="96" type="sub_section">
      <SectionTitle>
2.2 Semantic Relations in Noun Phrases
</SectionTitle>
      <Paragraph position="0"> Most of the research on relationships between nouns and modifiers deals with noun compounds, but these relationships also hold between nouns and adjective premodifiers or postmodifying prepositional phrases. Lists of semantic labels have been proposed, based on the theory that a compound expresses one of a small number of covert semantic relations.</Paragraph>
      <Paragraph position="1"> Levi (1978) argues that semantics and word formation make noun-noun compounds a heterogeneous class. She removes opaque compounds and adds nominal non-predicating adjectives. For this class Levi offers nine semantic labels. According to her theory, these labels represent underlying predicates deleted during compound formation. George (1987) disputes the claim that Levi's non-predicating adjectives never appear in predicative position.</Paragraph>
      <Paragraph position="2"> Warren (1978) describes a multi-level system of semantic labels for noun-noun relationships.</Paragraph>
      <Paragraph position="3"> Warren (1984) extends the earlier work to cover adjective premodifiers as well as nouns. The similarity of the two lists suggests that many adjectives and premodifying nouns can be handled by the same set of semantic relations.</Paragraph>
    </Section>
    <Section position="3" start_page="96" end_page="96" type="sub_section">
      <SectionTitle>
2.3 Recognizing Semantic Relations
</SectionTitle>
      <Paragraph position="0"> Programs that uncover the relationships in modifier-noun compounds often base their analysis on the semantics of the individual words (or a composition thereof). Such systems assume the existence of some semantic lexicon.</Paragraph>
      <Paragraph position="1"> Leonard's system (1984) assigns semantic labels to noun-noun compounds based on a dictionary that includes taxonomic and meronymic (partwhole) information, information about the syntactic behaviour of nouns and about the relationships between nouns and verbs. Finin (1986) produces multiple semantic interpretations of modifier-noun compounds. The interpretations are based on precoded semantic class information and domain-dependent frames describing the roles that can be associated with certain nouns. Ter Stal's system (1996) identifies concepts in text and unifies them with structures extracted from a hand-coded lexicon containing syntactic information, logical form templates and taxonomic information.</Paragraph>
      <Paragraph position="2"> In an attempt to avoid the hand-coding required in other systems, Vanderwende (1993) automatically extracts semantic features of nouns from online dictionaries. Combinations of features imply particular semantic interpretations of the relationship between two nouns in a compound.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>