<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1035">
  <Title>An Efficient Generation Algorithm for Lexicalist MT</Title>
  <Section position="7" start_page="265" end_page="265" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a polynomial complexity generation algorithm which can form part of any Shake-and-Bake style MT system with suitable grammars and information transfer. The transfer module is free to attempt structural transfer in order to produce the best possible first guess. We tested a TNCB-based generator in the SLEMaT MT system with the pathological cases described in (Brew, 1992) against Whitelock's original generation algorithm, and have obtained speed improvements of several orders of magnitude. Somewhat more surprisingly, even for short sentences which were not problematic for Whitelock's system, the generation component has performed consistently better.</Paragraph>
  </Section>
class="xml-element"></Paper>