<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-1016">
  <Title>Discourse Processing in MT: Problems in Pronominal Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
3. Treatment of Pronominal Translation
</SectionTitle>
    <Paragraph position="0"> In this paper, we will focus on the problems of translating English overt non-reflexive pronominals into Japanese. These l)ronominals must be mapped into 1) overt l)ronominals, 2) 'zibun', 3) pro, or 4) discourse pro in Japanese.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1. Role of Discourse
</SectionTitle>
      <Paragraph position="0"> To explain some exceptions on locality conditions and ambiguous cases in anaphora resolution, recent studies have focused on the role of discourse (Grosz 1981; Sidner 1983; Joshi &amp; Weinstein 1981; Kameyama 1985; Roberts 1986) and world knowledge. Discourse factors affecting anaphora resolution are discourse structure and discourse focus/center. This report concerns only the latter; in particular, the selection of focus and its maintenance. Following Grosz, we assume that a focus is the most salient NP in a sentence, and every sentence has one and only one focus 1. Often a focus is marked by the use of pronominal, stress, thematic role and particular syntactic constructions such as clefting, question, passivization, etc. However, there seems no clear generalization on the organization of the focus marking factors. We simply assume the most marked NP with respect to die number of found factors (asher &amp; Wada 1989; Alshawi 1987).</Paragraph>
      <Paragraph position="1"> We have adopted the Discourse Representation Structure (Kamp 1981) to represent a current discourse structure which will be appended to an f-structure representing a sentence. DRS+f-structure gives a ground for examining logical conditions based 1 We concern a local focus only, and multiple foci cases are excluded from our discussion.</Paragraph>
      <Paragraph position="3"> on the accessibility condition, and locality conditions such as disjoint reference on each anaphoric expression (cf. Roberts 1986).</Paragraph>
      <Paragraph position="4"> Now consider 4) discourse pro. Its characteristic is that it may not be bound in the current sentence, but must be bound by the focus in the previous discourse. In other words, when a pronominal cannot find its antecedent in the current DRS, we assume that it must be bound by the previous discourse focus unless the focus has been shifted, and in such a case we translate it as ~, a lexical zero pronominal.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.2. Proform Selection by FU
</SectionTitle>
      <Paragraph position="0"> On the other hand, when an antecedent is found in the DRS, the anaphoric link will be noted not only in DRS, but also in relevant f-structures via features such as Ant(ecedent) and Desc(endent) with a common index. However, we still need to determine which form should be used: pro, 'zibun', or overt pronominals. The selection should be syntactically made on the Japanese side since no additional information is available for the selection in the English f-structures.</Paragraph>
      <Paragraph position="1"> Let us discuss the syntactic mechanism for the proforrn selection. Suppose that a proform be lexically presented in each noun in the lexicon such as follows2: I ~ENDER msc GENDER msc )ROFORI'I 'he' PROFORid 'he' When the two shown above are anaphorically linked in a sentence, LFG offers a syntactic solution, namely, the Functional Uncertainty (Kaplan &amp; Maxwell 1988) 3. The link is represented by a functional-application equation (FU) such as follows: (2) &lt; ^/GF* \GF PREFORM &gt; = &lt; ^ PREFORM &gt; In the above FU, the second GF after the right slash represents an f-structure that dominates a possible antecedent, and the first GF* after the left slash, fcommanding path to the antecedent from the current f-structure 4. That is, the FU imposes a constraint such that the right-hand side of the equation in (2) represents an f-structure containing a pronominal, and if there is an f-structure within the path represented by the left-hand side of the equation, then it must be the case that their PROFORMs are unifiable 5.</Paragraph>
      <Paragraph position="2"> For the generation of surface PROFORMs, we assume that a pronominal element possesses a lexically unspecified PREFORM, and it will be specified by its antecedent. In other words, given that a pronominal and its antecedent are coindexed, an FU such as follows should be satisfied.</Paragraph>
      <Paragraph position="3">  (3) &lt; ^ / GF* \ GF* Ant &gt; =c &lt; ^ Desc &gt; 2plural PROFORMs should be assigned to NPs syntactically. 3The stone mechanism has been used in other cases such as the noun classifier selection for numeral expressions and negative scope domain setting by 'wa' in Japanese (Wada forthcoming).</Paragraph>
      <Paragraph position="4"> 4 This has been done by pointing the antecedent from the current l'-structure.</Paragraph>
      <Paragraph position="5"> 5 Note that the equation is far more powerful than this description.</Paragraph>
      <Paragraph position="6">  This equation can be solved only when the indices are identical. Once the equation (3) is solved, PREFORM will be unified between the antecedent and the pronominal 6 Selection on pro and 'zibun' can be considered as solving particularly restricted FU equations. For example, 'zibun' will be selected when the following</Paragraph>
      <Paragraph position="8"> This equation says that if there exists a SUBJ that fcommands GF(s) that may contain an adjunct which includes an f-structure in which the current pro resides, then it must be the case that the Ant value of that SUBJ and Desc value of the pro are identical.</Paragraph>
      <Paragraph position="9"> Each unspecified 'pro' will carry a set of equations, each of which selects a particular PREFORM disjunctively.</Paragraph>
      <Paragraph position="11"> The anaphora resolution mechanism in our program consists of three functional units: the DRS construction (DRSCONS), the salient element storing (SLSTOR), and the antecedent searching (ANSR).</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.1. DRSCONS
</SectionTitle>
      <Paragraph position="0"> This module constructs DRSs compositionally, following Montagovian tradition (Wada 8,: Asher 1986, Reyle 1988). Thus, we assume that a semantic representation, SMS, is appended to each F-structure.</Paragraph>
      <Paragraph position="1"> SMS is a pair &lt; SemType, DRS &gt;, where SemType is a semantic type.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>