<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-1406">
  <Title>De-Constraining Text Generation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
-1 Introduction
</SectionTitle>
    <Paragraph position="0"> This paper addresses the area of text generation known as microplanning \[Levelt1989, Panaget1994, Huang and Fiedler1996\], or sentence planning \[Rambow and Korelsky1992\]; \[Wanner and Hovy1996\].</Paragraph>
    <Paragraph position="1"> Microplanning involves low-level discourse structuring and marking, sentence boundary planning, clause*internal structuring and all of the varied subtasks involved in lexical choice, These complex tasks are often modularized and treated separately. The general argument is that since sentence planning tasks are not single-step operations, since they do not have to be performed in strict sequence, and since the planner's operation is non-deterministic, each sentence planning task should be implemented by a separate module or by several modules (see, e.g., \[Wanner and Hovy1996\]).</Paragraph>
    <Paragraph position="2"> Such an argument is natural if generation is viewed as a set of coarse-grained tasks. Indeed, with the exception of a few researchers (\[Elhadad et a1.1997\] and the incrementalists listed below), the task-oriented view is standard in the generation community. Unfortunately, task-oriented generation sets up barriers among the components of the generation process, primarily because, in a realistic scenario, the tasks are intertwined to a high degree. Overcoming these barriers has become a central topic in generation research (see below). In our approach the basis of modularization is sought in the nature of the input data to the generation process, in our case, a text meaning representation, formulated largely in terms of an ontology. This data-oriented approach is similar to that taken by many incremental generators \[De Smedt1990, Reithinger1992\], although these tend to concentrate on syntactic processing. But see \[Kilger1997\], who explicitly addresses microplanning. We feel that our work provides an optimal path between task-oriented generators (which face problems due to the interrelationships between the tasks) and traditional incremental generation (which does not take advantage of problem decomposition as discussed below).</Paragraph>
    <Paragraph position="3"> In what follows we describe our ontology-based modularization, the kind of constraints which can be automatically set up within such a paradigm, and the control mechanism we employ to process it.</Paragraph>
    <Paragraph position="4"> We focus on the task of lexicalization, but other microplanning tasks have been handled similarly.</Paragraph>
    <Paragraph position="5"> We conclude with a discussion of the avoidable barriers inherent in most current approaches, along  with their attempts at circumventing them, and how our approach eliminates many of the problems.</Paragraph>
    <Paragraph position="6"> We also point out differences between our approach and that of the incremental generators.</Paragraph>
  </Section>
class="xml-element"></Paper>