<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2094">
  <Title>Parameterization of the Interlingua in Machine Translation</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> The translation model described here is built on the basis of a parametric approach; thus, it is easy to change from one language to another (by setting syntactic and lexical switches for each language) without having to write a whole new processor for each language. This is an advance over other machine translation systems that require at least one language-8pecific processing module for each sourcelanguage/targetolanguage pair.</Paragraph>
    <Paragraph position="1"> The approach is interlingual: an underlying language-independent form of the source language is derived, and any of the three target languages, Spanish, English, or German, can be produced from this form. Perhaps the most important advance of UNITRAN is the mapping between the lexical-semantie level and the syntactic level. In particular, tile 8ys~ tern has been shown to select and realize the appropriate target-language words, despite the potential for syntactic and lexical divergences. The key to being able to provide a systematic mapping between languages is modularity: because the system has been partitioned into two different processing levels, there is a deeoupling of the syntactic and lexicalo semantic decisions that are made during the translation process. Titus, syntactic and LCS parameter settings may be specified for each language without hindering the processing that produces, and generates from, the interlingual form.</Paragraph>
  </Section>
class="xml-element"></Paper>