<?xml version="1.0" standalone="yes"?>
<Paper uid="A92-1007">
  <Title>Automatic Generation of Multimodal Weather Reports from Datasets</Title>
  <Section position="8" start_page="53" end_page="54" type="evalu">
    <SectionTitle>
7 Generation and composition
</SectionTitle>
    <Paragraph position="0"> The text generator converts the surface structure into text by making use of the phrasal lexicon. For some o the terminals of the surface structure it provides ready.</Paragraph>
    <Paragraph position="1"> made strings, while other terminals have to be refine( further. For example, if the regions &amp;quot;South Bulgaria' and &amp;quot;East Bulgaria&amp;quot; occur in the same phrase, the gener. ator will combine them into the contracted form &amp;quot;Soutt and East Bulgaria&amp;quot;. Whenever possible, the text gener.</Paragraph>
    <Paragraph position="2"> ator takes care of the diversity of lexical forms by pro viding different phrases for terminal nodes of the sam~ type (compare &amp;quot;much of Bulgaria&amp;quot; and &amp;quot;most areas&amp;quot; ii the example in Figure 3).</Paragraph>
    <Paragraph position="3"> The map generator interprets the map plan and con verts it into an image by rendering the successive state ments (cf. section 6.3). The maps contours as well as th~ various icons are prepared in advance and stored in th~ visual library. The text supplements, if any, are prepareC/ in the same way as ordinary text portions and attacheC/ to the bottom of the map.</Paragraph>
    <Paragraph position="4">  The formatter composes the document from components delivered by the generators. An enumeration structure is created from the constituting text portions by inserting the lexical representation of each external context as a heading of the corresponding portion. A table is composed of phrases produced by the text generator from a series of values extracted by the scanner.</Paragraph>
  </Section>
class="xml-element"></Paper>