<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2093">
  <Title>Planning texts by constraint satisfaction</Title>
  <Section position="13" start_page="646" end_page="647" type="concl">
    <SectionTitle>
8 Extensions
</SectionTitle>
    <Paragraph position="0"> Our method allows an exhaustive emnneration of solutions, but only within an elenmntary ti'a.nmwork tbr representing rhetorical and textual structure. We hot)e to gradually extend this frmnework to cover many phenonmna that are currently excluded: * Since its inlmt takes the form of a rhetorical structure tree, the text; strueturer inherits ally limitations of RST as a description of rhetorical organization.</Paragraph>
    <Paragraph position="1"> * We cover only three types of discourse commctive (subordillating conjmmtion, coordinating conjunction, conjuctive adverb).</Paragraph>
    <Paragraph position="2"> * At present there is no treatment of titles.</Paragraph>
    <Paragraph position="3"> * There is no treatment of relative clauses, which (:all be elnt)loyed for exami)le to realize the elaboration relation (Scott; and de Souza, 1990): Zovirax, which contains the antiviral agent aciclovir, is a smooth white cretan.</Paragraph>
    <Paragraph position="4"> * There is no treatinent of propositions that are expressed parenthetically.</Paragraph>
    <Paragraph position="5"> Zovirax, since it; is for you only, should never be given to other l)atients.</Paragraph>
    <Paragraph position="6"> Zovirax should never be given to other pall(mrs (the medicine is for you only).</Paragraph>
    <Paragraph position="7"> * We have omitted the colou-expansion pattern (Nunl)erg, 1.990) and some other features inthleneing i)unctuation (emi)hasis , quotation marks, parentheses).</Paragraph>
    <Paragraph position="8"> * We have not covered the integration of text with tloating items like diagrams, tal)les, or boxes. Two extensions that have already been iml)lemented are indentation and centering. We have exl)lained here how indentation is represented in text structure; the relevant constraints will be described elsewhere. Centering has been incorporated by assigning backward and forward centers to all 1)rot)ositions ill a comt)leted TS bcforc generating the wording; in this way, centering transitions can be evahlated before tactical generation begins, and TSs yielding good c(mtimlity of reference can be i)referred (Kibble aud Power, 1999).</Paragraph>
    <Paragraph position="9"> To use our approach ill 1)ractical applications, one must address the 1)roblem that the number of eandi(late solutions increases exi)onentially with the con&gt; plexity of the rhetorical structure --- measured, for exanll)le , by the mmfl)er of elementary propositions. lil informal trials we find that the numl)er of solutions is roughly 5 g-1 for all input with N propositions; this means that even for a short passage containing n dozen propositions, the text t)lanner would lind about 50 million solutions satisfying the hard  constraints. For texts of non-trivial length, there steins no alternative to sacrificing global ot)timality in the interests of efficiency. One option is to use a statistical optimization method such as a genetic algorithm (Mellish et al., 1998). In ICONOCLAST we have preferred a method of partial optimization in which the the text-structuring problem is split into parts, so that at each stage only a manageable part of the total solution is constructed. For instance, when planning a patient information leaflet, the semantic material could first be distributed among sections, then perhaps among t)aragraphs, thus spawning many small-scale text-structuring problems for which the search spaces would be measured in hundreds rather than billions.</Paragraph>
  </Section>
class="xml-element"></Paper>