<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0306">
  <Title>Investigating the Characteristics of Causal Relations in Japanese Text</Title>
  <Section position="3" start_page="37" end_page="37" type="intro">
    <SectionTitle>
2 Related work
</SectionTitle>
    <Paragraph position="0"> Liu (2004) analyzed the differences of usages of some Japanese connectives marking causal relations. The results are useful for accounting for an appropriate connective for each context within the documents. However Liu conducted no quantitative studies.</Paragraph>
    <Paragraph position="1"> Marcu (1997) investigated the frequency distribution of English connectives including because and since for implementation of rhetorical parsing. However, although Marcu's study was quantitative one, Marcu treated only explicit linguistic expressions with connectives. In the Timebank corpus (Pustejovsky et al., 2003), the causal relation information is included. However, the information is optional for implicit linguistic expressions.</Paragraph>
    <Paragraph position="2"> Although both explicit expressions and implicit expressions are treated in the Penn Discourse Tree-bank (PDTB) corpus (Miltsakaki et al., 2004), no information on causal relations is contained in this corpus.</Paragraph>
    <Paragraph position="3"> Altenberg (1984) investigated the frequency distribution of causal relation instances from some viewpoints such as document style and the syntactic form in English dialog data. Nishizawa (1997) also conducted a similar work using Japanese dialog data. Some parts of their viewpoints are overlapping with ours. However, while their studies focused on dialog data, our target is text documents. In fact, Altenberg treated also English text documents. However, our focus in this work is Japanese.</Paragraph>
  </Section>
class="xml-element"></Paper>