<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0607">
  <Title>Feeding OWL: Extracting and Representing the Content of Pathology Reports</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Clinical pathologists work with and produce vast amounts of data: images of biological samples and written reports of their findings. Digital Pathology is the cover term for a number of efforts to introduce digital processing into the work-flow of the pathologist. While previous projects have focussed on storage and distribution of images and reports (e.g. in Tele-Pathology-projects, (Slodowksa et al., 2002; Demichellis et al., 2002)), the work reported here explores the use of Natural Language Processing (NLP) and Semantic Web technologies to support a content-based storage and retrieval of case reports. The system that we are building, LUPUS (Lung Pathology System), consists of an NLP component (a robust parser) and a Semantic Web component (a domain ontology represented in OWL, and a Description Logic reasoner), which work closely together, with the domain ontology guiding the information extraction process.</Paragraph>
    <Paragraph position="1"> The remainder of the paper is organised as follows. In the next section we describe the context and intended application of the system, we discuss linguistic properties of the input material we are working with, and we give some details of the background ontology we are using. In Section 3 we go into the technical details of the process of extracting information from natural language reports and representing it in an OWL representation, after which we describe a preliminary evaluation. We close with discussing related work, and planned future work.</Paragraph>
  </Section>
class="xml-element"></Paper>