<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1005">
  <Title>Hierarchical Directed Acyclic Graph Kernel: Methods for Structured Natural Language Data</Title>
  <Section position="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> The experiments in this paper were designed to evaluated how the similarity measure reflects the semantic information of texts. In the task of Question Classification, a given question is classified into Question Type, which reflects the intention of the question. The Sentence Alignment task evaluates which sentence is the most semantically similar to a given sentence.</Paragraph>
    <Paragraph position="1"> The HDAG Kernel showed the best performance in the experiments as a similarity measure and as a kernel of the learning algorithm. This proves the usefulness of the HDAG Kernel in determining the similarity measure of texts and in providing an SVM kernel for resolving classification problems in NLP tasks. These results indicate that our approach, incorporating richer structures within texts, is well suited to the tasks that require evaluation of the semantical similarity between texts. The potential use of the HDAG Kernel is very wider in NLP tasks, and we believe it will be adopted in other practical NLP applications such as Text Categorization and Question Answering.</Paragraph>
    <Paragraph position="2"> Our experiments indicate that the optimal parameters of combination number a156 and decay factor a150 depend the task at hand. They can be determined by experiments.</Paragraph>
    <Paragraph position="3"> The original DSK requires exact matching of the tree structure, even when expanded (DSK') for flexible matching. This is why DSK' showed the worst performance. Moreover, in Sentence Alignment task, paraphrasing or different expressions with the same meaning is common, and the structures of the parse tree widely differ in general. Unlike DSK', SSK' and HDAG Kernel offer approximate matching which produces better performance.</Paragraph>
    <Paragraph position="4"> The structure of HDAG approaches that of DAG, if we do not consider the hierarchical structure. In addition, the structure of sequences (strings) is entirely included in that of DAG. Thus, the framework of the HDAG Kernel covers DAG Kernel and SSK.</Paragraph>
  </Section>
class="xml-element"></Paper>