<?xml version="1.0" standalone="yes"?>
<Paper uid="W03-2007">
  <Title>Makoto IWAYAMA</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Patent corpus processing should be centered around patent claim processing because claims are the most important part in patent specifications. It is common that claims written in Japanese are described in one sentence with peculiar style and wording and are difficult to understand for ordinary people. The peculiarity is caused by structural complexity of the sentences and many difficult terms used in the description. We have already proposed a framework to represent the structure of patent claims and a method to automatically analyze it. We are currently investigating a method to clarify terms in patent claims and to find the explanatory portions from the detailed description part of the patent specifications. Through both approaches, we believe we can improve readability of patent claims.</Paragraph>
  </Section>
class="xml-element"></Paper>