<?xml version="1.0" standalone="yes"?>
<Paper uid="A92-1033">
  <Title>Overview of Natural Language Processing of Captions for Retrieving Multimedia Data</Title>
  <Section position="6" start_page="231" end_page="231" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> The ability to use natural language for query specification and retrieval holds the most promise over keyword and keyphrase approaches. We believe that the restricted use of natural language in captions for multimedia data retrieval is a less difficult task than full natural language fact retrieval.</Paragraph>
    <Paragraph position="1"> We feel that we have a system that can be demonstrated and built upon not only for retrieving images but also other forms of multimedia data as well.</Paragraph>
  </Section>
class="xml-element"></Paper>