<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2223">
  <Title>A Pattern-based Machine Translation System Extended by Example-based Processing</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> While the World-Wide Web (WWW) has quickly turned the Internet into a treasury of information for every netizen, non-native English speakers now face a serious problem that textual data are more often than not written in a foreign language. This has led to an explosive popularity of machine translation (MT) tools in the world.</Paragraph>
    <Paragraph position="1"> Under these circumstances, we developed a machine translation system called PalmTree I which uses the pattern-based translation \[6, 7\] formalism. The key ideas of the pattern-based MT is to employ a massive collection of diverse transfer knowledge, and to select the best translation among the translation candidates (ambiguities). This is a natural extension of the example-based MT in the sense that we incorporate not only sentential correspondences (bilingual corpora) but every other level of linguistic (lexical, phrasal, and collocational) expressions into the transfer knowledge. It is also a rule-based counterpart to the word n-grams of the stochastic MT since our patterns intuitively captures the frequent collocations.</Paragraph>
    <Paragraph position="2"> Although the pattern-based MT framework is promising, there are some drawbacks. One is the speed, since it uses many rules when parsing. The other is inefficiency of usage of translation patterns, 1Using this system, IBM Japan releases a MT product called &amp;quot;Internet King of Translation&amp;quot; which can translate an English Web pages into Japanese.</Paragraph>
    <Paragraph position="3"> since it uses the exact-match when matching translation patterns with the input. We will describe several methods for accelerating the system performance for the former, and describe the extension by using the example-based processing \[4, 8\] for the latter.</Paragraph>
  </Section>
class="xml-element"></Paper>