<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-1017">
  <Title>The Automatic Generation of Formal Annotations in a Multimedia Indexing and Searching Environment</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7 Role of MUMIS for the Annotation of
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Multimedia Content
</SectionTitle>
      <Paragraph position="0"> To conclude, we would like to list the points where we think MUMIS will, directly or indirectly, contribute to extract and access multimedia content: a0 uses multimedia (MM) and multilingual information sources; a0 carries out multimedia indexing by applying information extraction to a well-delineated domain and using already existing information as constraints; a0 uses and extends advanced language technology to automatically create formal annotations for MM content; a0 merges information from many sources to improve the quality of the annotation database; a0 application of IE to the output of ASR and the combination of this with already existing knowledge; a0 definition of a complex information annotation structure, which is stored in a standard document type definition (DTD); a0 integration of new methods into a query interface which is guided by domain knowledge (ontology and multilingual lexica). So in a sense MUMIS is contributing in defining semantic structures of multimedia contents, at the level proposed by domain-specific IE analysis. The full machinery of IE, combined with ASR (and in the future with Image Analysis) can be used for multimedia contents development and so efficiently support cross-media (and crosslingual) information retrieval and effective navigation within multimedia information interfaces. There seems thus that this technolgy can play a highly relevant role for the purposes of knowledge detection and management. This is probably specially valid for the merging component, which is eliminating redundancies in the annotations generated from sets of documents and establishing complex reference resolutions, thus simplyfying the access to content (and knowledge) distributed over multiple documents and media.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>