<?xml version="1.0" standalone="yes"?>
<Paper uid="M98-1005">
  <Title>UNIVERSITY OF DURHAM: DESCRIPTION OF THE LOLITA SYSTEM AS USED IN MUC-7</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> This document describes the LOLITA system and how it was used to run the MUC tasks of named entity, co-reference and template element. Details of the system's performance are given for the walk-through articles as well as overall performance.</Paragraph>
    <Paragraph position="1"> LOLITA has been designed in such a way that the code implementing the MUC tasks is only a small part of the whole system. A core system provides complex facilities with the MUC system being built so that it utilises these facilities. Hence, after some background to the LOLITA project, the 'core' of LOLITA is described. This system description is substantially similar to that given for MUC-6 [1]. However, some important changes to the underlying core system have occurred since MUC-6 and these are presented in their own section. Following this is a description of changes that were required specifically for MUC-7.</Paragraph>
    <Paragraph position="2"> An analysis of the system's performance for the walk-through articles is presented together with an overall view of the system's performance. Prior to the conclusions a section on further and ongoing work is provided. This includes brief descriptions of some important work that is being undertaken, in particular: a re-engineering of the system which will result in a C++ version, and the addition of a large number of dictionary word definitions to the knowledge base.</Paragraph>
  </Section>
class="xml-element"></Paper>