<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1015">
  <Title>Example-based Machine Translation Based on Syntactic Transfer with Statistical Models</Title>
  <Section position="8" start_page="11" end_page="11" type="evalu">
    <SectionTitle>
4.2 Results
</SectionTitle>
    <Paragraph position="0"> Table 2 shows the results of the MT quality and translation speed among each method.</Paragraph>
    <Paragraph position="1"> First, comparing the baseline with the statistical generations (Bottom-up and All Search), the MT quality of statistical generation improved in all evaluation metrics. Accordingly, the models of statistical MT are effective for improving the MT quality of example-based MT.</Paragraph>
    <Paragraph position="2"> Next, comparing Bottom-up with All Search, the MT quality of bottom-up generation was slightly low. Bottom-up generation locally applies the translation model to a partial tree. In other words, the probability is calculated without word alignment linked to the outside of the tree. This result indicates that the results of bottom-up generation are not equal to the global optimal solution. Comparing LM Only with the statistical generations, the MT quality of ranks A+B+C by subjective evaluation significantly decreased. This is because the n-gram language model used here does not consider output length, and shorter translations are preferred. Although the language model was effective to some degree, it could not evaluate the equivalence of the translation and the input sentence. Therefore, we concluded that the translation model is necessary for improving MT quality. Finally, focusing on translation speed, the worst time for Bottom-up generation was dramatically faster than that for All Search. Bottom-up generation effectively uses shared nodes of the target tree, so it can improve translation speed. Therefore, bottom-up generation is suitable for tasks that require real-time processing, such as spoken dialogue translation.</Paragraph>
  </Section>
class="xml-element"></Paper>