<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1005">
  <Title>Improving Statistical Word Alignment with a Rule-Based Machine Translation System</Title>
  <Section position="5" start_page="321" end_page="321" type="evalu">
    <SectionTitle>
6 Discussion
</SectionTitle>
    <Paragraph position="0"> The error rate reductions in this paragraph are obtained from Table 2. The error rate reductions in Table 3 are omitted.</Paragraph>
    <Paragraph position="1"> Our method also achieves much better results on multi-word alignment than other methods.</Paragraph>
    <Paragraph position="2"> However, our method only obtains one third of the correct alignment links. It indicates that it is the hardest to align the multi-word units.</Paragraph>
    <Paragraph position="3"> Readers may pose the question &amp;quot;why the rule-based translation system performs better on word alignment than the translation dictionary?&amp;quot; For single word alignment, the rule-based translation system can perform word sense disambiguation, and select the appropriate Chinese words as translation. On the contrary, the dictionary can only list all translations. Thus, the alignment precision of our method is higher than that of the dictionary method. Figure 5 shows alignment precision and recall values under different similarity values for single word alignment including null links. From the figure, it can be seen that our method consistently achieves higher precisions as compared with the dictionary method. The t-score value (t=10.37, p=0.05) shows the im- null ary. The result is shown in Table 5 in Section 5.2. This is because (1) the translation system can automatically recognize English phrases with higher accuracy than the translation dictionary; (2) The translation system can detect separated phrases while the dictionary cannot. For example, for the sentence pairs in Figure 6, the solid link lines describe the alignment result of the rule-base translation system while dashed lines indicate the alignment result of the translation dictionary. In example (1), the phrase &amp;quot;be going to&amp;quot; indicates the tense not the phrase &amp;quot;go to&amp;quot; as the dictionary shows. In example (2), our method detects the separated phrase &amp;quot;turn ... on&amp;quot; while the dictionary does not. Thus, the dictionary method produces the wrong alignment link.</Paragraph>
  </Section>
class="xml-element"></Paper>