<?xml version="1.0" standalone="yes"?>
<Paper uid="J89-2001">
  <Title>A PRAGMATICS-BASED APPROACH TO ELLIPSIS RESOLUTION</Title>
  <Section position="2" start_page="0" end_page="76" type="abstr">
    <SectionTitle>
1 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Incomplete utterances are common in communication between humans. They range from sentences that fail to include all requisite semantic information to syntactically incomplete sentence fragments. In many cases, these utterances cannot be understood in isolation, but must be interpreted within the established context.</Paragraph>
    <Paragraph position="1"> Precisely how this should be done is a difficult problem for natural language systems.</Paragraph>
    <Paragraph position="2"> One might suggest that the problem be avoided in man-machine communication by training human users to employ only syntactically and semantically complete utterances. However, this does not appear to be feasible, as demonstrated in an empirical study conducted by Carbonell (1983) in which it was shown that human users find it easy to avoid complex syntactic structures but difficult to avoid incomplete utterances.</Paragraph>
    <Paragraph position="3"> Even if it were possible to train users to avoid incomplete utterances, these restrictions would be undesirable. Constraining man-machine communication to only a subset of the utterances normally employed by humans would force users to give less attention to their problem solving goals in order to concentrate more on the preciseness of their utterances. In addition, it appears that fragmentary utterances are not merely a result of sloppy communication. Although every utterance has a discourse goal (a conversational or communicative goal such as answering a question or seeking clarification), elliptical fragments are often used to accomplish discourse goals that would require more effort to convey with a complete sentence. For example, in the following dialog ~, Speaker 2's fragment expresses doubt about the proposition stated by Speaker 1.</Paragraph>
    <Paragraph position="4"> Example 1 Speaker 1: &amp;quot;The Korean jet shot down by the Soviets was a spy plane.&amp;quot; Speaker 2: &amp;quot;With 269 people on board?&amp;quot; However, a complete sentence such as Speaker 2: &amp;quot;Was the Korean jet shot down by the Soviets a spy plane with 269 people on board?&amp;quot; fails to adequately communicate the doubt conveyed by the previous fragment. Only a more complex sentence that marks the discourse goal, such as Speaker 2: &amp;quot;How can you think that the Korean jet shot down by the Soviets was a spy plane, when it had 269 people on board?&amp;quot; will accomplish this objective.</Paragraph>
    <Paragraph position="5"> Thus a robust natural language interface must handle the kinds of incomplete utterances normally used by humans. To do otherwise is to prohibit communication that humans regard as natural, and therefore detract from their ability to communicate as effectively with machines as they do with one another.</Paragraph>
    <Paragraph position="6"> Contextual ellipsis in dialog is the use of a sentence fragment (a syntactically incomplete utterance), along with the context established by the preceding dialog, to communicate a complete thought and accomplish a Copyright 1989 by the Association for Computational Linguistics. Permission to copy without fee all or part of this material is granted provided that the copies are not made for direct commercial advantage and the CL reference and this copyright notice are included on the first page. To copy otherwise, or to republish, requires a fee and/or specific permission. 0362-613X/89/010075-96-$ 03.00 Computational Linguistics, Volume 15, Number 2, June 1989 75 Sandra Carberry A Pragmatics-Based Approach to Ellipsis Resolution speech act 2. Such fragments are often referred to as intersentential ellipsis since they appear between sentences in a dialog. It can be seen, however, that understanding intersentential ellipsis often depends more on pragmatic knowledge, such as the inferred task-related plan and discourse goals motivating the speaker, than on the syntactic structure or semantic content of preceding utterances. This is illustrated by Examples 2 and 3, in which Speaker l's communicated goal and the relevant plans for accomplishing it play a  the necessary background and should be invited for an interview.&amp;quot; In Example 2, Speaker l's goal is to cash a check, and relevant plans can include a subplan for getting a particular distribution of paper money; in Example 3, Speaker l's goal is hiring programming consultants, perhaps for an introductory programming course, and the relevant plans for doing this include a subplan for identifying the best applicant.</Paragraph>
    <Paragraph position="7"> Previous research on understanding intersentential ellipsis has emphasized syntactic and semantic strategies (Hendrix et al. 1978; Waltz 1978; Weischedel and Sondheimer 1982; Carbonell 1983), but the contributions of the speaker's plans and goals to the interpretation of ellipsis has hitherto been inadequately explored. One objective of our research has been to investigate a plan-based framework for understanding intersentential ellipsis that occurs in task-oriented dialogs. Our work shows that elliptical fragments can be viewed as highlighting aspects of the information-seeker's task-related plan, with the focus of attention in the plan providing the context in which the fragment should be understood. null But identifying the aspect of the speaker's plan highlighted by the ellipsis is not enough to understand the utterance. As shown by Grosz (1979), a speaker may pursue several different kinds of goals with a single utterance. For example, an information-seeker has the long-term goal of performing a task comprised of subtasks; this hierarchical structure produces a set of task-related goals. The information seeker is attempting to construct a plan for his underlying task, resulting in plan formation goals. In addition, each utterance pursues a more immediate discourse goal, such as requesting information or seeking clarification. As has been shown by several researchers (Mann et al. 1977; Reich- null man 1978; Pollack et al. 1982), one must determine not only the element of the task being addressed by an utterance, but also the discourse goal being fulfilled by it. Previous research on understanding ellipsis has ignored this aspect. Thus a second objective of our research has been to formulate a strategy for recognizing discourse goals communicated by elliptical fragments. Our work indicates that mutual beliefs and expectations developed from the preceding dialog play a major role in identifying the intent behind intersentential ellipsis.</Paragraph>
    <Paragraph position="8"> Our processing framework coordinates many knowledge sources, including discourse expectations, inferred beliefs, the information-seeker's inferred task-related plan, and focusing strategies, to produce a rich interpretation of ellipsis. It is the first interpretation strategy to address the problem of identifying the discourse goal accomplished via an intersentential elliptical fragment.</Paragraph>
    <Paragraph position="9"> As a result, this pragmatics-based framework understands elliptical fragments that other systems cannot handle.</Paragraph>
  </Section>
class="xml-element"></Paper>