<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2162">
  <Title>Improving SMT quality with morpho-syntactic analysis</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this pal)er, we address the question of how morl)hological and syntactic analysis can help statistical machine translation (SMT). In our apl)roach, we introduce several transtbrmations to the source string (in our experiments the source language is German) to demonstrate how linguistic knowledge can improve translation resuits especially in the cases where, the token-type ratio (nmnber of training words versus nmnber of vocabulary entries) is unthvorable.</Paragraph>
    <Paragraph position="1"> After reviewing the statistical approach to machine translation, we first explain our motivation for examining additional knowledge sources. We then present our approach in detail.</Paragraph>
    <Paragraph position="2"> Ext)erimental results on two bilingual German-English tasks are reported, namely the VERBMOBIL and the EUTRANS task. Finally, we give an outlook on our fllture work.</Paragraph>
  </Section>
class="xml-element"></Paper>