<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1085">
  <Title>Definiteness Predictions for Japanese Noun Phrases*</Title>
  <Section position="3" start_page="0" end_page="519" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> The problem of article selection when translating from Japanese into any language requiring the use of articles has only been addressed systematically by a few authors.</Paragraph>
    <Paragraph position="1"> (Murata and Nagao, 1993) define a heuristic rule base for definiteness assignment, consisting of 86 weighted rules. These rules use surface in- null formation in a sentence to estimate the referential property of each noun. During processing, each applicable rule assigns confidence weights to the three possible referential properties 'definite', 'indefinite' and 'generic'. These values are added up for each property, and the one with the highest score will be assigned to the noun in question. If no rule applies, the default value is 'indefinite'. This approach assigns the correct value in 85,5% of the cases when used with the training data, and 68,9% with unseen data.</Paragraph>
    <Paragraph position="2"> (Bond et al., 1995) show how the percentage of noun phrases generated with correct use of articles and number in a Japanese to English machine translation system can be increased by applying heuristic rules to distinguish between 'generic', 'referential' and 'ascriptive' uses of noun phrases. These rules are ordered in a hierarchical manner, with later rules over-ruling earlier ones. In addition, for each noun phrase use there are specific rules, based on linguistic information, that assign definiteness to the noun phrases. Overall, in their system, insertion of the correct article can be improved by 12% yielding a correctness level of 77%.</Paragraph>
    <Paragraph position="3"> In contrast to these approaches relying on monolingual indicators alone, (Siegel, 1996) proposes to assign definiteness during the transfer process. In a first stage, all lexically defined definiteness attributes are assigned. To all cases not covered by this, a set of preference rules is applied, if their translation equivalent in the target language is a noun. In addition to linguistic indicators from both the source and target language, the rules also take a stack of referents mentioned previously in the discourse into account. This combined approach is very successful, assigning the correct definiteness attributes to 98% of all relevant noun phrases in the training data.</Paragraph>
    <Paragraph position="4"> In the approach described in the next section, we have taken up the idea of using both linguistic and contextual information for the assignment of definiteness attributes to Japanese noun phrases. However, instead of using merely a rule base, we propose a monotone algorithm based on a linguistic rule hierarchy followed by a context checking mechanism.</Paragraph>
  </Section>
class="xml-element"></Paper>