<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1030">
  <Title>Example-Based Machine Translation in the Pangloss System</Title>
  <Section position="13" start_page="172" end_page="172" type="ackno">
    <SectionTitle>
9 Future Enhancements
</SectionTitle>
    <Paragraph position="0"> Since PanEBMT is a fairly new implementation, there is still much that could be done to enhance it. Among the improvements being considered are: improving the qnality of the dictionary (in progress); supporting one-to-many or many-to-one associations for alignment; optimizing the test-function weights; other alignment algorithms; using linguistic information such as morphological variants and source-language synonymy to increase the number of matches against the corpus; using approximate matchings when no exact matches exist in the corpus; and using of a classifier algorithm to remove redundancy from the corpus (suggested by C. Domashnev).</Paragraph>
  </Section>
class="xml-element"></Paper>