<?xml version="1.0" standalone="yes"?>
<Paper uid="J81-4001">
  <Title>Focusing for Interpretation of Pronouns I</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2. Research on Anaphora
</SectionTitle>
    <Paragraph position="0"> The role of context and inference, as well as syntax and semantics, on anaphor interpretation have been explored extensively. A brief look at these explorations indicates the necessity of a new approach. Research on anaphora falls into four broad categories:  1. General heuristics for finding antecedents \[Winograd 1972\] 2. Syntactic and semantic constraints on anaphora \[Katz &amp; Fodor 1963, Woods et al. 1976, Chomsky 1976, Lasnik 1976, Reinhart 1976, Walker 1976\] 3. Use of inference to find antecedents \[Charniak 1972, Rieger 1974, Hobbs 1976\] 4. Analysis of relations among objects in a discourse  context \[Grosz 1977, Lockman 1978, Reichman 1978, Webber 1978, Hobbs 1979\] Rather than review each approach, I point out the contributions of each type to a theory of pronoun interpretation.</Paragraph>
    <Paragraph position="1"> General heuristics, as a means of choosing antecedents, predict reliably in a large number of typical examples. However, no simple characterization fits the wide variety of cases where they fail (see Winograd 1972 and Hobbs 1977); furthermore, the heuristic approach is not theoretically grounded and cannot offer a unified approach to the phenomena.</Paragraph>
    <Paragraph position="2"> Semantic selectional restrictions, based on the Katz-Fodor theory of semantic markers, and used by many computational linguists, can reduce the space of possible antecedents, but they cannot be used to eliminate all possibilities, as the example below illustrates (where feeling soft can be said of either a mud pack or one's face): s2 Put the mud pack on your face. Notice how soft it feels.</Paragraph>
    <Paragraph position="3"> Syntactic restrictions, on logical form \[Chomsky 1976\] and on constituent structure \[Lasnik 1976, Reinhart 1976\], stipulate conditions in which a pronoun and a noun phrase must have disjoint reference, as shown below.</Paragraph>
    <Paragraph position="4"> s3 * Near Dan, he saw a snake.</Paragraph>
    <Paragraph position="5"> s4 * The man whose house he bought went gold digging in Alaska.</Paragraph>
    <Paragraph position="6"> These rules, however, do not stipulate the interpretation of a pronoun; in a general theory they serve only as a filtering condition on the class of possible cospecifications. Furthermore, syntactic restrictions must also stipulate the disjoint reference conditions on reflexive pronouns although no adequate account of these conditions has yet appeared.</Paragraph>
    <Paragraph position="7"> Work by researchers in artificial intelligence on inference led to methods for forward and backward chaining of inferences to bind the pronoun, represented as a free variable, with some piece of knowledge; with this approach, the pronoun's interpretation was the value bound to the free variable. This approach revealed that inferences about world knowledge are often needed to interpret pronouns. However, these methods failed to control the inference process sufficiently. Charniak, attempting to resolve this problem, American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 219 Candace L. Sidner Focusing for Interpretation of Pronouns proposed demons that would &amp;quot;wake up&amp;quot; in the appropriate situation (that is, processes which could themselves notice when they were to begin processing). But a large cache of demons would be required, and no assurance could be given that demons would exist in every situation. Most significantly, this proposal said nothing about the situation where two or more demons might apply (who gets control? how are the decisions made?). Furthermore all of the inference-based approaches to pronoun interpretation fail to offer any theoretical approach because they rely on a simple mechanism, (simple variable binding between pronoun and some other phrase) which does not apply in many uses of anaphors, such as D1.</Paragraph>
    <Paragraph position="8"> Discourse approaches to anaphora include a technique similar to the inference method; one identifies sentence pairs and determines their semantic relationship as one of elaboration, similarity, contrast, parallel structure; the pronouns are interpreted by variable binding between items of the sentence pairs \[Hobbs 1979\]. Webber 1978, using a notion of &amp;quot;discourse identifications&amp;quot; (that contain certain semantic and discourse content) similar to the notion of specification, stipulates constraints on the representation of relations among items mentioned in a discourse.</Paragraph>
    <Paragraph position="9"> Grosz \[1977, 1978, 1981\] illustrates how parts of a speaker's knowledge, relevant to a discourse segment, are highlighted via focusing, a process that reflects what a speaker says and the nature of the knowledge in the space. She shows that the structure of a task affects what items will be focused on in the discourse. Reichman has expanded this paradigm by describing context spaces, delineated by their topics. Her analysis shows that within a context space only certain items may be pronominalized. She leaves open the questions: What is the recognition procedure for determining a context space? How does one identify its topic? How does the hearer determine the interpretation of a pronoun, i.e., how does a hearer decide which highly focused items act as the co-specification of a pronoun? All these approaches support the view that since hearers do not have privileged access to a speaker's mind, other than through what a speaker says, imposing structure on the speaker's discourse will provide a framework for establishing the interpretation of pronouns. null The remainder of this paper defines the concept of speaker's foci and shows that they can be used to choose specifications for personal pronouns. The rules for choosing interpretations are stated within a framework that shows: * how to control search in inferring by a new method called constraint checking, * how to take advantage of syntactic, semantic and discourse constraints on interpretation, how to generalize the treatment of personal pronouns, to serve as a framework for the theory of interpretation for all anaphors.</Paragraph>
  </Section>
class="xml-element"></Paper>