<?xml version="1.0" standalone="yes"?>
<Paper uid="P90-1004">
  <Title>Empirical Study of Predictive Powers of Simple Attachment Schemes for Post-modifier Prepositional Phrases</Title>
  <Section position="1" start_page="0" end_page="23" type="abstr">
    <SectionTitle>
US West Advanced Technologies
6 June 1990
Abstract
</SectionTitle>
    <Paragraph position="0"> This empirical study attempts to find answers to the question of how a natural language (henceforth NL) system could resolve attachment of prepositional phrases (henceforth PPs) by examining naturally occurring PP attachments in typed dialogue.</Paragraph>
    <Paragraph position="1"> Examination includes testing predictive powers of existing attachment theories against the data. The result of this effort will be an algorithm for interpreting PP attachment.</Paragraph>
    <Paragraph position="2"> Introduction Difficulty in resolving structural ambiguity involving PPs arises because of the great variety of syntactic structures which PPs can modify and the varying distances PPs may be from the constituents with which they are associated. Simple schemes to resolve attachments utilize information drawn from reported tendencies in the human parsing mechanism, such as the preference for PPs to attach to constituents that immediately precede them. It is always tempting to utilize such schemes in computer NL processors because they provide clear models for resolution that are both easy and cheap (in terms of steps involved) to implement.</Paragraph>
    <Paragraph position="3"> The problem with these schemes is that they can easily be made to fail by manipulating parameters that they 'know' nothing about, such as semantics, context, and intonation. Clearly, more elaborate schemes for attachment resolution are needed, but what these schemes should contain and how they should be implemented remain open.</Paragraph>
    <Paragraph position="4"> This study attempts to find answers to the question of how a computer program should resolve attachment by examining naturally occurring PP attachments in a typed dialogue domain drawn from a study by Brunner, Whittemore, Ferrara, and Hsu (1989). Various previously developed theories of PP attachment are tested against the data to see how well they predict correct attachments of PPs in the typed dialogues. The result of this effort will be a hypothesis of attachment resolution that seems to fit the data.</Paragraph>
    <Paragraph position="5"> Empirical overview The methods for generating the 13 naturally occurring dialogues are described in Brunner, et al. (1989). In essence, this study employed a &amp;quot;wizard of Oz&amp;quot; paradigm in which a human confederate -- the Wizard - simulates an advanced computer system engaged in written/interactive dialogue with the experimental participant. Participants of the study were each asked to plan a specific travel agenda of their choice with information obtained solely by typing natural language messages and requests through a VT220 terminal to a human-assisted travel information system located in a separate room. In response to this, the Wizard, who had access to both computerized and hard-copy travel data, was instructed to engage in constructive and free-form dialogue with the participant in order to best obtain the reservations and flight information required by them. Each dialogue took one and a half hours to complete, allowing enough time for about 70 sentences per dialogue  for a total of 910 sentences.</Paragraph>
    <Paragraph position="6"> In another study, Whittemore, Ferrara, and Brunner (1989) quantify the occurrence of PPs in the 13 dialogues in terms of the syntactic types to which they attach and the overall syntactic environments in which they appear. Data is presented in terms of Tension Sites to illustrate possible syntactic attachment interpretations and actual interpretations that occurred. For instance in the sentence John eats his bananas in his backyard, potential attachment ambiguity lies in the fact that the PP in his backyard can attach to the noun phrase object his bananas or to the verb eats. Such positions were referred to as Tension Sites. All such Tension Sites for sentences with PPs were recorded along with actual attachments. Some instances were simple as in the example above with only a minimum of Tension Sites, while others were quite involved and had up to seven Tension Sites in which a verb and np-object along with the objects of five other prepositions were available as attachment sites. Of the 910 sentences in the 13 dialogues, 745 had instances of potential ambiguity in attachment. Much of the analysis presented in this paper is drawn from the Whittemore, et al. study.</Paragraph>
    <Paragraph position="7"> Theories of Preferenclng for Post-modifier</Paragraph>
  </Section>
class="xml-element"></Paper>