<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1019">
  <Title>A Comparative Study on Reordering Constraints in Statistical Machine Translation</Title>
  <Section position="9" start_page="0" end_page="0" type="concl">
    <SectionTitle>
8 Conclusions
</SectionTitle>
    <Paragraph position="0"> We have described the ITG constraints in detail and compared them to the IBM constraints. We draw the following conclusions: especially for long sentences the ITG constraints allow for higher flexibility in word-reordering than the IBM constraints. Regarding the Viterbi alignment in training, the baseline ITG constraints yield a similar coverage as the IBM constraints on the Verbmobil task. On the Canadian Hansards task the baseline ITG constraints were not sufficient. With the extended ITG constraints the coverage improves significantly on both tasks. On the Canadian Hansards task the coverage increases from about 87% to about 96%.</Paragraph>
    <Paragraph position="1"> We have presented a polynomial-time search algorithm for statistical machine translation based on the ITG constraints and its extension for the generation of word graphs. We have shown the translation results for the Verbmobil task. On this task, the translation quality of the search with the base-line ITG constraints is already competitive with the results for the IBM constraints. Therefore, we expect the search with the extended ITG constraints to outperform the search with the IBM constraints.</Paragraph>
    <Paragraph position="2"> Future work will include the automatic extraction of the bilingual grammar as well as the use of this grammar for the translation process.</Paragraph>
  </Section>
class="xml-element"></Paper>