<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2155">
  <Title>Generation of Paraphrases from Ambiguous Logical Forms</Title>
  <Section position="2" start_page="0" end_page="919" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> This paper describes a new generation method that produces multiple paraphrases from a semantic input which may contain ambiguities. The method is an extension of the chart based generation algorithm described in Kay (1996). The focus in this presentation is on generating multiple paraphrases and the ability to operate on logical forms that contain more than one semantic analysis. The lnotivation for this is to enable a situation (particularly in machine translation) where the resolution of ambiguity is postponed to after the generation process. This may open the possibility for considering target language statistics (Knight and Hatzivassiloglou, 1995; Dagan et al., 1991) or more generally for applying other criteria to select the &amp;quot;best&amp;quot; translation, which take into account properties of both languages - for example, prefering ambiguity preserving translations. It may also enable different kinds of interactions between the translation system and the human expert who operates it- tbr instance, disambiguation by a monolingual in the target language.</Paragraph>
    <Paragraph position="1"> The first demonstration of using charts for generation appeared in Shieber (1988). In that paper the emphasis was to show that a uniform architecture can be used for both parsing and generation, however the conception of the chart was limited and the generation algorithm did not appear to be sufficiently attractive.</Paragraph>
    <Paragraph position="2"> Kay (1996) provides a mole general view of the chart structure which is designed to provide for generation advantages comparable to those it provides for parsing. Neumann (1994) proposes another version of a uniform chart architecture where the same data structures are used for both generation and parsing.</Paragraph>
    <Paragraph position="3"> In this discussion of chart generation we will tbcus on one key advantage of the chart structure: the fact that equivalent phrases cml fit into larger structures once, regardless of the number of alternatives that they represent. This is achieved by collapsing different deriwttions that cover the same subset of input (and have the same syntactic potential) under a single edge that represents an equivalence class. This propeity is the basis for the efficiency gained by using charts as it allows a compact representation in which a polynomial number of edges can potentially encode exponentially many derivations. Thus, the ability to recognize equivalence is an important aspect of chart processing and it is essential that it will be available to the generation process.</Paragraph>
    <Paragraph position="4"> We will uot describe the underlying generation algorithm in detail but we assume that familiarity with chart parsing is sufficient for understanding the proposed method - the generator can be thought of as a parser that takes logical forms as input and produces strings as analyses. Like a packed parsing forest which represents nmltiple parsing results, the chart generator produces a &amp;quot;packed generation forest&amp;quot; to represent the various string realizations of the semantics. In the method we propose here, these forests are annotated with information that enables keeping track of the rela~ tion between pieces of the semantics and the various phrases that express them. We will concentrate on a detailed description of these annotations as they are a crucial component of our method and they are the major difference between the current proposal and the one described in Kay (1996). Belbre we do that we will sketch a version of Kay's algorithm, emphasizing data representations rather than algorithmic details.</Paragraph>
    <Paragraph position="5"> We will also follow Kay in adopting a &amp;quot;flat&amp;quot; representation of event semantics to represent the logical forms (Davidson, 1980; Parsons, 1990). This style of seman- null tics fits the operation of the generation algorithm very well and it is attractive to translation since it allows for flexibility and simplicity with regard to syntactic realization and treatment of structural mismatches between syntax and semantics. The flat structure is also convenient for encoding unresolved ambiguities (Copestake et al., 1996).</Paragraph>
  </Section>
class="xml-element"></Paper>