<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1064">
  <Title>Dependency-based Sentence Alignment for Multiple Document Summarization</Title>
  <Section position="5" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Results and Discussion
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
5.1 Single Document Summarization Data
</SectionTitle>
      <Paragraph position="0"> Table 5 shows the results of the baseline method (i.e., without DTPs) with the best a56 ; Table 6 shows  the results of using DTPs with the best a57 and a64 , which are shown in brackets. From the results, we can see the effectiveness of DTPs because Table 6 shows better performance than Table 5 in most cases. Table 7 shows the difference between Tables 5 and 6. DTPs improved the results of BOW by about five points. The best result is DTP with ESK. However, we have to admit that the improvements are relatively small for single document data. On the other hand Tree Kernel did not work well since it is too sensitive to slight differences. This is known as a weak point of Tree Kernel (Suzuki et al., 2003). According to the tables, BOW is outperformed by the other methods except Tree Kernel. These results show that word co-occurrence is important. Moreover, we see that sequential patterns are better than consequential patterns, such as the N-gram.</Paragraph>
      <Paragraph position="1"> Without DPTs, ESK is worse than WSK. However, ESK becomes better than WSK when we use DTPs. This result implies that word senses are disambiguated by syntactic information, but more examination is needed.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
5.2 Multiple Document Summarization Data
</SectionTitle>
      <Paragraph position="0"> Table 8 shows the results of the baseline method with the besta56 for multiple document data while Table 9 shows the result of using DTPs with the best a57 and a64 , (in brackets). Compared with the single document summarization results, the F-measures are low. This means that the sentence alignment task is more difficult in multiple document summarization than in single document summarization. This is because sentence compaction, combination, and integration are common.</Paragraph>
      <Paragraph position="1"> Although the results show the same tendency as the single document summarization case, more improvements are noticed. Table 10 shows the difference between Tables 8 and 9. We see improvements in 10 points in ESK, WSK, and BOW. In multiple document summarization, sentences are often reorganized. Therefore, it is more effective to decompose a sentence into DTP sets and to compute similarity between the DTPs.</Paragraph>
      <Paragraph position="2"> Moreover, DTP(ESK) is once again superior to DTP(WSK).</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
5.3 Parameter Tuning
</SectionTitle>
      <Paragraph position="0"> For ESK and WSK, we have to choose parameters, a57 and a64 . However, we do not know an easy way of finding the best combination of a57 and a64 . Therefore, we tuned these parameters for a development set. The experimental results show that the best a57 is 2 or 3. However, we could not find a consistently optimal value of a64 . Figure 5 shows the F-measure with various a64 for a57a88a58a89a60 . The results shows that the F-measure does not change very much in the middle range a64 , [0.4,0.6] which suggests that good results are possible by using a middle range a64 .</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>