<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1026">
  <Title>Sentence Planning as Description Using Tree Adjoining Grammar *</Title>
  <Section position="3" start_page="0" end_page="198" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Since (Meteer, 1991), researchers in natural language generation have recognized the need to refine and reorganize content after the rhetorical organization of arguments and before the syntactic realization of phrases.</Paragraph>
    <Paragraph position="1"> This process has been named sentence planning (Rambow and Korelsky, 1992). Broadly speaking, it involves aggregating content into sentence-sized units, and then selecting the lexical and syntactic elements that are used in realizing each sentence. Here, we consider this second process.</Paragraph>
    <Paragraph position="2"> The challenge lies in integrating constraints from syntax, semantics and pragmatics. Although most generation systems pipeline decisions (Reiter, 1994), we believe the most efficient and flexible way to integrate constraints in sentence planning is to synchronize the decisions. In this paper, we provide a natural framework for dealing with interactions and ensuring contextually appropriate output in a single pass. As in (Yang et al., 1991), Lexicalized Tree Adjoining Grammar (LTAG) provides an *The authors thank Aravind Joshi, Mark Steedman, Martha Palmer, Ellen Prince, Owen Rambow, Mike White, Betty Birner, and the participants of INLG96 for their helpful comments on various incarnations of this work. This work has been supported by NSF and IRCS graduate fellowships, NSF grant NSF-STC SBR 8920230, ARPA grant N00014-94 and ARt grant DAAH04-94-G0426.</Paragraph>
    <Paragraph position="3"> abstraction of the combinatorial properties of words. We combine LTAG syntax with declarative specifications of semantics and pragmatics of words and constructions, so that we can build the syntax and semantics of sentences simultaneously. To drive this process, we take description as the paradigm for sentence planning. Our planner, SPUD (Sentence Planner Using Descriptions), takes in a collection of goals to achieve in describing an event or state in the world; SPUD incrementally and recursively applies lexical specifications to determine which entities to describe and what information to include about them.</Paragraph>
    <Paragraph position="4"> Our system is unique in the streamlined organization of the grammar, and in its evaluation both of contextual appropriateness of pragmatics and of descriptive adequacy of semantics.</Paragraph>
    <Paragraph position="5"> The organization of the paper is as follows. In section 2, we review research on generating referring expressions and motivate our treatment of sentences as referring expressions. Then, in section 3, we present the linguistic underpinnings of our work. In section 4, we describe our algorithm and its operation on an example.</Paragraph>
    <Paragraph position="6"> Finally, in section 5 we compare our system with related approaches.</Paragraph>
    <Paragraph position="7"> 2 Sentences as referring expressions Our proposal is to treat the realization of sentences as parallel to the construction of referring expressions, and thereby bring to bear modern discourse-oriented theories of semantics and the idea that language use is INTEN-TIONAL ACTION.</Paragraph>
    <Paragraph position="8"> Semantically, a DESCRIPTION D is just an open formula.</Paragraph>
    <Paragraph position="9"> D applies to a sequence of entities when substituting them for the variables in D yields a true formula. D REFERS to C jUSt in case it distinguishes c from its DISTRACTORS-that is D applies to c but to no other salient alternatives. Given a sufficiently rich logical language, the meaning of a natural language sentence can be represented as a description in this sense, by assuming sentences refer to entities in a DISCOURSE MODEL, cf. alternative semantics (Karttunen and Peters, 1979; Rooth, 1985).</Paragraph>
    <Paragraph position="10"> Pragmatic analyses of referring expressions model speakers as PLANNING those expressions to achieve several different kinds of intentions (Donellan, 1966; Appelt,  1985; Kronfeld, 1986). Given a set of entities to describe and a set of intentions to achieve in describing them, a plan is constructed by applying operators that enrich the content of the description until all intentions are satisfied. Recent work on generating definite referring NPs (Reiter, 1991 ; Dale and Haddock, 1991; Reiter and Dale, 1992; Horacek, 1995) has emphasized how circumscribed instantiations of this procedure can exploit linguistic context and convention to arrive quickly at short, unambiguous descriptions. For example, (Reiter and Dale, 1992) apply generalizations about the salience of properties of objects and conventions about what words make base-level attributions to incrementally select words for inclusion in a description. (Dale and Haddock, 1991) use a constraint network to represent the distractors described by a complex referring NP, and incrementally select a property or relation that rules out as many alternatives as possible. Our approach is to extend such NP planning procedures to apply to sentences, using TAG syntax and a rich semantics.</Paragraph>
    <Paragraph position="11"> Treating sentences as referring expressions allows us to encompass the strengths of many disparate proposals.</Paragraph>
    <Paragraph position="12"> Incorporating material into descriptions of a variety of entities until the addressee can infer desired conclusions allows the sentence planner to enrich input content, so that descriptions refer successfully (Dale and Haddock, 1991) or reduce it, to eliminate redundancy (McDonald, 1992). Moreover, selecting alternatives on the basis of their syntactic, semantic, and pragmatic contributions to the sentence using TAG allows the sentence planner to choose words in tandem with appropriate syntax (Yang et al., 1991), in a flexible order (Elhadad and Robin, 1992), and, if necessary, in conventional combinations (Smadja and McKeown, 1991; Wanner, 1994).</Paragraph>
  </Section>
class="xml-element"></Paper>