<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-2009">
  <Title>Learning Meronyms from Biomedical Text</Title>
  <Section position="3" start_page="0" end_page="49" type="intro">
    <SectionTitle>
1Oxford English Dictionary, Second Edition, 1989.
</SectionTitle>
    <Paragraph position="0"> such as the familiar relations of synonymy and hyponymy (Cruse, 2000). Meronymy relates the lexical item for a part to that for a whole, equivalent to the conceptual relation of partOf 2. Example 1 shows a meronym. When we read the text, we understand that the frontal lobes are not a new entity unrelated to what has gone before, but part of the previously mentioned brain.</Paragraph>
    <Paragraph position="1"> (1) MRI sections were taken through the brain. Frontal lobe shrinkage suggests a generalised cerebral atrophy.</Paragraph>
    <Paragraph position="2"> The research described in this paper considers meronymy, and its extraction from text. It is taking place in the context of the Clinical e-Science Framework (CLEF) project 3, which is developing information extraction (IE) tools to allow querying of medical records. Both IE and querying require domain knowledge, whether encoded explicitly or implicitly. In IE, domain knowledge is required to resolve co-references between textual entities, such as those in Example 1. In querying, domain knowledge is required to expand and constrain user expressions. For example, the query in Example 2 should retrieve sarcomas in the pelvis, but not in limbs.</Paragraph>
    <Paragraph position="3"> (2) Retrieve patients on Gemcitabine with advanced sarcomas in the trunk of the body.</Paragraph>
    <Paragraph position="4"> The part-whole relation is critical to domain knowledge in biomedicine: the structure and function of biological organisms are organised along partitive axes. The relation is modelled in several medical knowledge resources (Rogers and Rector, 2000),  but they are incomplete, costly to maintain, and unsuitable for language engineering. This paper looks at simple lexico-syntactic techniques for learning meronyms. Section 2 considers background and related work; Section 3 introduces an algorithm for relation extraction, and its implementation in the PartEx system; Section 4 considers materials and methods used for experiments with PartEx. The experiments are reported in Section 5, followed by conclusions and suggestions for future work.</Paragraph>
  </Section>
class="xml-element"></Paper>