<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1098">
  <Title>A PARSER COPING WITH SELF-REPAIRED JAPANESE UTTERANCES AND LARGE CORPUS-BASED EVALUATION</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Self-repair(Levelt 1988) is a repair of utterance by speaker him/herself. A truman speaker makes self-repairs very frequently in spontaneous speedt. (Blackmer and Mitton 1991) reported that self-repairs are made once every 4.8 seconds in dialogues taken fi'om radio talk shows.</Paragraph>
    <Paragraph position="1"> Self-repair is one ldnd of &amp;quot;permissible illformedness&amp;quot;, that is a human listener can feel ill-formedness in it hut he/she is able to recognize its intended meaning. Thus your partner does not need to interrupt dialogue.</Paragraph>
    <Paragraph position="2"> Itow do you feel if your partner interrupts dialogue every 5 seconds to ask &amp;quot;What do you mean?&amp;quot; or so? You will give up dialogue or choose means of writing. Speaking without self-repair is the most difficult modality of natural language communication.</Paragraph>
    <Paragraph position="3"> The goal of our work is to make a dialogue system coping with self-repaired utterances. In this paper we propose a parser called SERUP(SElf-Repaired Utterance Parser), which plays a major part in understanding a self-repaired utterance. That is, because our approach is to translate a self-repaired utterance (Ex.1) into a well-formed version that does not contain self-repair (Ex.2) and parse the well-formed one, we do not need to change the subsequent processes. null \[Ex.1\] And fi'om green left to pink, er, from blue left to pink (from (Levelt 1988)) \[Ex.2\] And fi'om blue left to pink SERUP uses some linguistic clues to translate utterances, those include a repetition, an unknown word and/or an isolated word. We describe how SERUP uses these clues.</Paragraph>
    <Paragraph position="4"> To evaluate SERUP, we analyze a large corpus that contains spontaneous dialogues over telephone. From the result, we estimate that SI';RUP works well with 88.1% of 1,082 self-repairs in the corpus.</Paragraph>
  </Section>
class="xml-element"></Paper>