<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-2045">
  <Title>An Interactive Japanese Parser for Machine Translation</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> JAWB is currently being used to accumulate correct parse trees for a corpus of texts. The accumulated data are vital for the development of our machine translation system for at least two reasons: null 1. The transfer component, which generates an English syntactic structure from a Japanese syntactic structure, is difficult to develop without having enough error-free input data, that is, Japanese parse trees.</Paragraph>
    <Paragraph position="1"> 2. The accumulated parse trees are used as reliable linguistic data from which various statistical data are obtained in order to refine the grammar rules.</Paragraph>
    <Paragraph position="2"> We believe that interactive source language analysis is a promising approach to practical machine translation not only because it may significantly reduce the task of post editing, which should be carried out by a professional translator, but also because tile cost-saving effect is multiplied when the same text is translated into several different languages.</Paragraph>
  </Section>
class="xml-element"></Paper>