<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-0810">
  <Title>Linear order as higher-level decision: Information Structure in strategic and tactical generation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The aim of this paper is to describe an architecture that addresses how information structure can be integrated into strategic and tactical generation.</Paragraph>
    <Paragraph position="1"> We focus primarily here on the tactical aspect of how word order (henceforth: WO) may function as a means of realizing information structure. The approach we take is multilingually applicable. It is implemented in KPML (Bateman, 1997b; Bateman, 1997a) and has been tested for Czech, Bulgarian and Russian as three Slavonic languages with different WO properties, as well as for English. The algorithm itself is not KPML-specific: it combines the idea of WO constraints posed by the grammar, with a complementary mechanism of default ordering based on information structure. The algorithm could thus be applied in other systems wich allow multiple sources of ordering constraints.</Paragraph>
    <Paragraph position="2"> Information structure is a means that a speaker employs to indicate that some parts of a sentence meaning are context-dependent (&amp;quot;given&amp;quot;), and that others are context-affecting (&amp;quot;new&amp;quot;). Information structure is therefore an inherent aspect of sentence meaning, and it contributes in an important way to the overall coherence of a text.</Paragraph>
    <Paragraph position="3"> While it is commonly accepted that information structuring is a major source of constraints for the organization of a given content in a particular linear order in many languages, there is very little work in Natural Language Generation that explicitly models this relation.</Paragraph>
    <Paragraph position="4"> From a practical perspective, in the most commonly employed generation systems such as KPML, FUF (Elhadad, 1993; Elhadad and Robin, 1997) or REALPRO (Lavoie and Rambow, 1997), linear ordering comes as a by-product of other grammatical choices. This is fine for tactical generation components and it is sufficient for languages with grammatically determined WO ('fixed' WO languages), such as English or Chinese. However, most languages have some WO variability and this variation usually reflects information structure. When languages in which linear order is primarily pragmatically determined are involved, such as the Slavonic languages we have dealt with, a number of problems become immediately apparent.</Paragraph>
    <Paragraph position="5"> A comprehensive account of WO variation for natural language generation that is reusable across languages is thus required. Such an account needs to represent linearization as an explicit decision-making process that involves both the representation of the language-specific linear ordering possibilites and the representation of the language-specific (and possibly cross-linguistically valid) motivations for particular linearizations. Again, while the former is catered for in most tactical generation systems, only selected aspects of the latter have been dealt with and only for selected languages (e.g., (Hoffman, 1994; Hoffman, 1995; Hakkani et al., 1996)).</Paragraph>
    <Paragraph position="6"> For example, (Hoffman, 1994) proposes a treatment of WO in Turkish using a categorial grammar framework (CCG, (Steedman, 2000)) and relating this to Steedman's (earlier) account of information structure (Steedman, 1991). However, the most important issue, that of providing an integrated account of how information structure guides the choice of (or, is realized by) linear ordering, is left unsolved (Kruijff, 2001).</Paragraph>
    <Paragraph position="7"> Given that in many languages, information structure is the major driving force for WO variation, it is indeed the most straighforward idea to couple an account of information structure with the choice of linear ordering. However, for multilingual application, the particular challenge is to develop a solution that can be applied, no matter at which point on the free-to-fixed WO cline a language is located.</Paragraph>
    <Paragraph position="8"> The approach to WO proposed in this paper is a move in exactly this direction. We start in a5 2 with presenting data from Czech, German and English that motivate the perspective we take on information structure, and its role in generating coherent discourse. In a5 3 we introduce the linguistic notions employed in the present account. In a5 4 we discuss how information structure fits into a general system architecture, and we discuss the implementation of the strategic generation component on the basis of KPML. We continue with an elaboration of the role of information structure in tactical generation, presenting an algorithm for generating contextually appropriate linearization, given a sentence's information structure, and illustrate its implementation on Czech and English examples (a5 5). We conclude the paper with a summary (a5 6).</Paragraph>
  </Section>
class="xml-element"></Paper>