<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2163">
  <Title>Recognition of the Coherence Relation between Te-linked Clauses</Title>
  <Section position="8" start_page="994" end_page="995" type="evalu">
    <SectionTitle>
5 Experiment and Discussion
</SectionTitle>
    <Paragraph position="0"> An experiment of recognizing coherence relations of te-linkage were done for 280 sentences which were randomly extracted from EDR Corpus (EDR, 1995).</Paragraph>
    <Paragraph position="1"> The analysis results are shown in Table 4, where the coherence relations in the sentences were classified into 7 categories by authors and compared with the outputs of the program.</Paragraph>
    <Paragraph position="2"> The relations are not balanced in number. This seems to be due to the genre of texts from which the test sentences were picked up (most of them were news articles). The numbers in parentheses show those of test sentences that matched with the fixed expressions in Table 1.</Paragraph>
    <Paragraph position="3"> The precision on the whole is 82%. This shows that to a large extent we can cope with the problem to recognize the coherence relations between clauses (at least when linked by re), given the event types of the clauses and the fixed expressions in the lexicon. Most of errors are caused by ambiguity of the relation. There were many examples which were difficult even for humans to make clear judgements. This reflects the fact that the coherence relations do not have definite borders.</Paragraph>
    <Paragraph position="4"> However, there were some errors which show a crucial limitation of our method. This appears as the bad marks in both precision and recall for the Concession relation, even though the number is small. For example, there is a test sentence such as follows: (19) ano hito-wa 82sai-ni natte, annani koukisin ippal-da.</Paragraph>
    <Paragraph position="5"> that person-TOP 82-years-old-DAT become-te, so curiosity be-full-PRES &amp;quot;Although that person is 82 years old, (he/she) is full of curiosity.&amp;quot;  Since the combination of the event type here is I(BECOME,BE), our program gave it the Circumstance relation as a default. However, we know that in general the person who is 82 years old is not so curious, therefore the Concession relation arises. Thus, our common sense knowledge is crucial to our recognition of the coherence relations. In (Hovy and Maier, 1993), they classified the Concession relation as interpersonal (i.e., author-and/or addresseerelated) rather than ideational (i.e., semantic), since they defined it as &amp;quot;one of the text segments raises expectations which are contradicted/violated by the other.&amp;quot; The use of interpersonal relations is predicated mainly on the interests, beliefs, and attitudes of addressee and/or author. To deal with this problem, we must incorporate the notion of intentional structure and focus space structure (Grosz and Sidner, 1986).</Paragraph>
    <Paragraph position="6"> Since we have focused on te-linkage in this paper, we need not to consider how clauses are combined.</Paragraph>
    <Paragraph position="7"> However, to detect the discourse structure, we need to extend the method so as to deal with the relations between sentences. We must estimate some kind of reliable scores among possible segments and choose the relation having the maximum score (Kurohashi and Nagao, 1994). These issues remain to be studied in the future.</Paragraph>
  </Section>
class="xml-element"></Paper>