<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2119">
  <Title>Using a Broad-Coverage Parser for Word-Breaking in Japanese</Title>
  <Section position="3" start_page="823" end_page="826" type="concl">
    <SectionTitle>
5. Conclusion
</SectionTitle>
    <Paragraph position="0"> We have shown that a practical, broad-coverage parser can be implemented without requiring the word-breaking component to return a single segmentation analysis, and that it can at the same time achieve high accuracy in POS-labeled word-breaking. Separating the tasks of word ident~/'l'cation and best sequence selection offers flexibility in enhancing both recall and precision without sacrificing either at the cost of the other. Our results show that morphological and syntactic information alone can resolve most word-breaking ambiguities. Nonetheless, some ambiguities require semantic and contextual information. For example, the following sentence allows two parses corresponding to two word-breaking analyses, of which the first is semantically preferred:  (1) ocha-ni haitte-irtt arukaroido tea-in contain-ASP alkaloid &amp;quot;the alkaloid contained in lea&amp;quot; (2) ocha-ni-ha itte-iru arukatwido tea-in-TOP go-ASP alkaloid  * ? the alkaloid that has gone to the tea&amp;quot; Likewise, the sentence below allows two different interpretations of the morpheme de, either as a locative marker (1) or as a copula (2). Both interpretations are syntactically and semantically wflid; only contextual information can resolve the ambiguity.</Paragraph>
    <Paragraph position="1">  (1) minen-ha isuraeru-de aru next year-TOP Israel-LOC be-held &amp;quot;It will be held in Israel next year&amp;quot;. (2) rainen-ha isuraeru de-artt next year-TOP Israel be-PP, ES  &amp;quot;It will be Israel next year&amp;quot;.</Paragraph>
    <Paragraph position="2"> In both these sentences, we create syntactic trees for all syntactically valid interpretations, leaving the ambiguity intact. Such ambiguities can only be resolved with semantic and contextual information eventually made available by higher processing components. This will be Ihe focus of our ongoing rese.arclt.</Paragraph>
  </Section>
class="xml-element"></Paper>