<?xml version="1.0" standalone="yes"?>
<Paper uid="A94-1023">
  <Title>Understanding Location Descriptions in the LEI System</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Many biological specimens collected in the past 1 are labeled with only an English description of their location of collection. 2 To perform any statistical or spatial analysis of this historical data, these descriptions must be converted into geodetic coordinates (latitude-longitude or UTM), a time-consuming process that requires eyestraining poring over maps to search for each location.</Paragraph>
    <Paragraph position="1"> 1Current collectors can use hand-held satellite-based geopositioning systems to record collection coordinates.</Paragraph>
    <Paragraph position="2"> 2There are an estimated several hundred millions of such labeled specimens.</Paragraph>
    <Paragraph position="3"> To automate this process requires understanding the natural language descriptions, reasoning about the spatial relations described by the natural language, and mapping these into a geographical object base to derive the collection coordinates.</Paragraph>
  </Section>
class="xml-element"></Paper>