<?xml version="1.0" standalone="yes"?>
<Paper uid="N03-1011">
  <Title>Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
1.1 Problem description
</SectionTitle>
      <Paragraph position="0"> An important semantic relation for several NLP applications is the part-whole relation, or meronymy. Consider the text: The car's mail messenger is busy at work in the mail car as the train moves along. Through the open side door of the car, moving scenery can be seen. The worker is alarmed when he hears an unusual sound. He peeks through the door's keyhole leading to the tender and locomotive cab and sees the two bandits trying to break through the express car door.</Paragraph>
      <Paragraph position="1"> There are six part-whole relations in this text: 1) the mail car is part of the train, 2) the side door is part of the car, 3) the keyhole is part of the door, 4) the cab is part of the locomotive, 5) the door is part of the car, and 6) the car is part of the express train (the last two in the compound noun express car door).</Paragraph>
      <Paragraph position="2"> Understanding part-whole relations allows Question Answering systems to address questions such as &amp;quot;What are the components of X?, What is X made of? and others. Question Answering, Information Extraction and Text Summarization systems often need to identify relations between entities as well as synthesize information gathered from multiple documents. More and more knowledge intensive techniques are used to augment statistical methods when building advanced NLP applications.</Paragraph>
      <Paragraph position="3"> This paper provides a method for deriving semantic constraints necessary to discover part-whole relations.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
1.2 Semantics of part-whole relation
</SectionTitle>
      <Paragraph position="0"> There are different ways in which we refer to something as being a part of something else, and this led many researchers to claim that meronymy is a complex relation that &amp;quot;should be treated as a collection of relations, not as a single relation&amp;quot; (Iris et al. , 1988).</Paragraph>
      <Paragraph position="1"> Based on linguistic and cognitive considerations about the way parts contribute to the structure of the wholes, Winston, Chaffin and Hermann (Winston et al. , 1987) determined in 1987 six types of part-whole relations: Component-Integral object (wheel - car), Member-Collection (soldier - army), Portion-Mass (meter - kilometer), Stuff-Object (alcohol - wine), Feature-Activity (paying - shopping), and Place-Area (oasis - desert).</Paragraph>
      <Paragraph position="2"> The part-whole relations in WordNet are classified into three basic types: Member-of (e.g., UK IS-MEMBER-OF NATO), Stuff-of (e.g., carbon IS-STUFF-OF coal), and all other part-whole relations grouped under the general name of Part-of (e.g., leg IS-PART-OF table). In this paper we lump together all the part-whole relation types, but if necessary, one can train the system separately on each of the six meronymy types to increase the learning accuracy.</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
1.3 Previous work
</SectionTitle>
      <Paragraph position="0"> Although part-whole relations were studied by philosophers, logicians, psychologists and linguists, not much work has been done to automatically identify the  meronymy relation in text. Hearst (Hearst, 1998) developed a method for the automatic acquisition of hypernymy relations by identifying a set of frequently used and unambiguous lexico-syntactic patterns. Then, she tried applying the same method to meronymy, but without much success, as the patterns detected also expressed other semantic relations.</Paragraph>
      <Paragraph position="1"> In 1999, Berland and Charniak (Charniak, 1999) applied statistical methods on a very large corpus to find part-whole relations. Using Hearst's method, they focused on a small set of lexico-syntactic patterns that frequently refer to meronymy and a list of 6 seeds representing whole objects. Their system's output was an ordered list of possible parts according to some statistical metrics. The accuracy obtained for the first 50 parts was 55%.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>