<?xml version="1.0" standalone="yes"?>
<Paper uid="A00-1020">
  <Title>Multilingual Coreference Resolution</Title>
  <Section position="7" start_page="147" end_page="147" type="evalu">
    <SectionTitle>
4 Results
</SectionTitle>
    <Paragraph position="0"> The foremost contribution of SWIZZLE was that it improved coreference resolution over both English and Romanian texts when compared to monolingual coreference resolution performance in terms of precision and recall. Also relevant was the contribution of SNIZZLE to the process of understanding the cultural differences expressed in language and the way these differences influence coreference resolution. Because we do not have sufficient space to discuss this issue in detail here, let us state, in short, that English is more economical than Romanian in terms of referential expressions. However the referential expressions in Romanian contribute to the resolution of some of the most difficult forms of coreference in English.</Paragraph>
    <Section position="1" start_page="147" end_page="147" type="sub_section">
      <SectionTitle>
4.1 Precision and Recall
</SectionTitle>
      <Paragraph position="0"> Table 4 summarizes the precision results for both English and Romanian coreference. The results indicate that the English coreference is more precise than the Romanian coreference, but SNIZZLE improves coreference resolution in both languages.</Paragraph>
      <Paragraph position="1"> There were 64% cases when the English coreference was resolved by a heuristic with higher priority than the corresponding heuristic for the Romanian counterpart. This result explains why there is better precision enhancement for the English coreference.</Paragraph>
      <Paragraph position="2">  advantage of the data-driven coreference resolution over other methods is based on its better recall performance. This is explained by the fact that this method captures a larger variety of coreference patterns. Even though other coreference resolution systems perform better for some specific forms of reference, their recall results are surpassed by the data-driven approach. Multilingual coreference in turn improves more the precision than the recall of the monolingual data-driven coreference systems.</Paragraph>
      <Paragraph position="3"> In addition, Table 5 shows that the English coreference results in better recall than Romanian coreference. However, the recall shows a decrease for both languages for SNIZZLE because imprecise coreference links are deleted. As is usually the case, deleting data lowers the recall. All results were obtained by using the automatic scorer program developed for the MUC evaluations.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>