<?xml version="1.0" standalone="yes"?>
<Paper uid="P92-1039">
  <Title>RIGHT ASSOCIATION REVISITED *</Title>
  <Section position="3" start_page="0" end_page="285" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Kimball (1973) proposes the parsing strategy of Right Association (RA). RA resolves modifiers attachment ambiguities by attaching at the lowest syntactically permissible position along the right frontier. Many authors (among them Wilks 1985, Schubert 1986, Whittemore et al. 1990, and Weischedel et al. 1991) incorporate RA into their parsing systems, yet none rely on it solely, integrating it instead with disambiguation preferences derived from word/constituent/concept co-occurrence based. On its own, RA performs rather well, given its simplicity, but it is far from adequate: Whittemore et al. evaluate RA's performance on PP attachment using a corpus derived from computer-mediated dialog.</Paragraph>
    <Paragraph position="1"> They find that RA makes correct predictions 55% of the time. Weischedel et al., using a corpus of news stories, report a 75% success rate on the general case of attachment using a strategy Closest Attachment which is essentially RA. In the work cited above, RA plays a relatively minor role, as compared with co-occurrence based preferences.</Paragraph>
    <Paragraph position="2"> The status of RA is very puzzling, consider:.</Paragraph>
    <Paragraph position="3">  (1) a. John said that Bill left yesterday.</Paragraph>
    <Paragraph position="4"> b. John said that Bill will leave yesterday.</Paragraph>
    <Paragraph position="5"> &amp;quot;I wish to thank Bob Frank, Beth Ann Hockey, Yonng-Snk Lee,  Steedman, and the anonymous referees for their helpful suggestions. This research has been supported by the following grants: DARPA N00014-90-J-1863, ARt DAAL03-89-C-0031, NSF IRI 90-16592, Ben Franklin 91S.30&amp;quot;/8C-1.</Paragraph>
    <Paragraph position="6">  (2) In China, however, there isn't likely to be any silver lining because the economy remains guided primarily by the state.</Paragraph>
    <Paragraph position="7"> (from the Penn Treebank corpus of Wall Street Journal articles) On the one hand, many naive informants do not see the ambiguity of la and are often confused by the putatively semantically unambiguous lb - a strong RA effect. On the other hand (2) violates RA with impunity. What is it that makes RA operate so strongly in 1 but disappear in 2? In this paper I argue that it is an aspect of the declarative linguistic competence that is operating here, not a principle of parsing.</Paragraph>
  </Section>
class="xml-element"></Paper>