<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0406">
  <Title>Capturing Disjunction in Lexicalization with Extensible Dependency Grammar</Title>
  <Section position="3" start_page="0" end_page="41" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In text generation the term lexicalization (Reiter and Dale, 2000) refers to deciding which among a choice of potentially applicable lexical items realizing a given intended meaning are actually going to take part in a generated utterance. It can be regarded as a general, necessary generation task -especially if one agrees that the term task does not necessarily imply pipelining -- and remarkably pervasive at that. For instance, even though the realization of such a phrase as &amp;quot;a ballerina&amp;quot; owes much to referring expression generation, a complementary task, it is still a matter of lexicalization whether to prioritize that specific phrase over all its possible legitimate alternates, e.g. &amp;quot;a female dancer&amp;quot;, &amp;quot;a dancing woman&amp;quot; or &amp;quot;a dancing female person&amp;quot;. However, prior to the statement of prioritizing criteria or selection preferences and rather as the very substratum thereto, the ultimate matter of lexicalization is exactly alternation, choice -in one word, disjunction.</Paragraph>
    <Paragraph position="1"> Given the combinatorial nature of language and specifically the interchangeability of lexical items yielding hosts of possible valid solutions to one same instance lexicalization task, disjunction may well become a major source of (combinatorial) complexity. Our subject matter in this paper is solely disjunction in lexicalization as a basis for more advanced lexicalization models, and our purpose is precisely to describe a constraint-based model that (i) captures the disjunctive potential of lexicalization, i.e. allows the generation of all mutually paraphrasing solutions (according to a given language model) to any given lexicalization task, (ii) ensures well-formedness, especially ruling out over-redundancy (such as found in &amp;quot;[?]a dancing female dancer/ballerina/woman&amp;quot;) and syntactic anomalies (&amp;quot;[?]a dancer woman&amp;quot;), and does so (iii) modularly, in that not only are concerns neatly separated (e.g. semantics vs. syntax), but also solutions are reusable, and future extensions, likely to be developed with no change to current modules, (iv) efficiently, having an implementation yielding strong propagation and thus prone to keep complexity at acceptable levels, and (v) synergicly, inasmuch as it promotes the interplay between modules (namely syntax and semantics) and seems compatible with the concept of integrated generation architectures (Reiter and Dale, 2000), i.e. those in which tasks are not executed in pipeline, but are rather interleaved so as to avoid failed or suboptimal choices during search.</Paragraph>
    <Paragraph position="2"> We build upon the Extensible Dependency Grammar (XDG) (Debusmann et al., 2004b; Debusmann et al., 2004a; Debusmann et al., 2005) model and its CP implementation in Oz (Van Roy and Haridi, 2004), namely the XDG Develop- null In fact, all those appealing goals of modularity, efficiency and synergy are innate to XDG and the XDK, and our work can most correctly be regarded as the very first attempts at equipping XDG for generation and fulfilling its bidirectional promise.</Paragraph>
    <Paragraph position="3"> The paper proceeds as follows. Section 2 provides background information on XDG and the XDK. Section 3 motivates our lexicalization disjunction model and describes it both intuitively and formally, while Section 4 presents implementation highlights, assuming familiarity with the XDK and focusing on the necessary additions and modifications to it, as well as discussing performance. Finally, in Section 5 we conclude and discuss future work.</Paragraph>
  </Section>
class="xml-element"></Paper>