<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1053">
  <Title>A Hierarchical Account of Referential Accessibility</Title>
  <Section position="4" start_page="5" end_page="5" type="relat">
    <SectionTitle>
3 VT and Structural Ambiguity
</SectionTitle>
    <Paragraph position="0"> The fact that VT considers only the nuclear-satellite distinction and ignores rhetorical labeling has practical ramifications for anaphora resolution systems that rely on discourse structure to determine the DRA for a given RE.</Paragraph>
    <Paragraph position="1"> (Marcu, et al., 1999) show that over a corpus of texts drawn from MUC newspaper texts, the Wall Street Journal corpus, and the Brown Corpus, reliable agreement among annotators is consistently obtained for discourse segmentation and assignment of nuclear-satellite status, while agreement on rhetorical labeling was less reliable (statistically significant for only the MUC texts). This means that even when there exist differences in rhetorical labeling, vein expressions can be computed and used to determine DRAs.</Paragraph>
    <Paragraph position="2"> VT also has ramifications for evaluating the viability of different structural representations for a given text, at least for the purposes of reference resolution. Like syntactic parsing, discourse parsing typically yields several interpretations, and one of the a priori tasks for further analysis of the parsed texts is to choose one from among potentially several alternative structures. Marcu (1996) showed that using only rhetorical relations, as many as five different structures can be identified for some texts.</Paragraph>
    <Paragraph position="3"> Considering intention-based relations can yield even more alternatives. For anaphora resolution, the choice of one structure over another may have significant impact. For example, an RST tree for (6) using rhetorical relations is given in Figure 8; Figure 9 shows another RST tree for the same text, using intention-based relations. If we compute the vein expressions for both representations, we see that the vein for segment C6 in the intentional representation is &lt;A6 B6 C6&gt;, whereas in the rhetorical representation, the vein is &lt;(B6), C6&gt;. That is, under the constraints imposed by VT, John is not available as a referent for he in C6 in the rhetorical version, although John is clearly the appropriate antecedent. Interestingly, the intention-based analysis is skewed to the right and thus is a &amp;quot;better&amp;quot; representation according to the criteria outlined in (Marcu, 1996); it also eliminates the left-satellite that was shown to pose problems for stack-based approaches. It is therefore likely that the intention-based analysis is &amp;quot;better&amp;quot; for the purposes of anaphora resolution.</Paragraph>
    <Paragraph position="4"> (6) A6. Tell John to bring the car home by 5.</Paragraph>
    <Paragraph position="5"> B6. That way I can get to the store before it closes.</Paragraph>
    <Paragraph position="6"> C6. Then he can finish the bookshelves tonight.</Paragraph>
  </Section>
class="xml-element"></Paper>