<?xml version="1.0" standalone="yes"?>
<Paper uid="P02-1003">
  <Title>Generation as Dependency Parsing</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Existing algorithms for realization from a flat input semantics all have runtimes which are exponential in the worst case. Several different approaches to improving the runtime in practice have been suggested in the literature - e.g. heuristics (Brew, 1992) and factorizations into smaller exponential subproblems (Kay, 1996; Carroll et al., 1999). While these solutions achieve some measure of success in making realization efficient, the contrast in efficiency to parsing is striking both in theory and in practice.</Paragraph>
    <Paragraph position="1"> The problematic runtimes of generation algorithms are explained by the fact that realization is an NP-complete problem even using just context-free grammars, as Brew (1992) showed in the context of shake-and-bake generation. The first contribution of our paper is a proof of a stronger NP-completeness result: If we allow semantic indices in the grammar, realization is NP-complete even if we fix a single grammar. Our alternative proof shows clearly that the combinatorics in generation come from essentially the same sources as in parsing for free word order languages. It has been noted in the literature that this problem, too, becomes NP-complete very easily (Barton et al., 1987).</Paragraph>
    <Paragraph position="2"> The main point of this paper is to show how to encode generation with a variant of tree-adjoining grammars (TAG) as a parsing problem with dependency grammars (DG). The particular variant of DG we use, Topological Dependency Grammar (TDG) (Duchier, 2002; Duchier and Debusmann, 2001), was developed specifically with efficient parsing for free word order languages in mind. The mere existence of this encoding proves TDG's parsing problem NP-complete as well, a result which has been conjectured but never formally shown so far. But it turns out that the complexities that arise in generation problems in practice seem to be precisely of the sort that the TDG parser can handle well. Initial experiments with generating from the XTAG grammar (XTAG Research Group, 2001) suggest that our generation system is competitive with state-of-the-art chart generators, and indeed seems to run in polynomial time in practice.</Paragraph>
    <Paragraph position="3"> Next to the attractive runtime behaviour, our approach to realization is interesting because it may provide us with a different angle from which to look for tractable fragments of the general realization problem. As we will show, the computation that takes place in our system is very different from that in a chart generator, and may be more efficient in some cases by taking into account global information to guide local choices.</Paragraph>
    <Paragraph position="4"> Plan of the Paper. We will define the problem we want to tackle in Section 2, and then show that it is NP-complete (Section 3). In Section 4, we sketch the dependency grammar formalism we use. Section 5 is the heart of the paper: We show how to encode TAG generation as TDG parsing, and discuss some examples and runtimes. We compare our approach to some others in Section 6, and conclude and discuss future research in Section 7.</Paragraph>
    <Paragraph position="5"> Computational Linguistics (ACL), Philadelphia, July 2002, pp. 17-24. Proceedings of the 40th Annual Meeting of the Association for</Paragraph>
  </Section>
class="xml-element"></Paper>