<?xml version="1.0" standalone="yes"?>
<Paper uid="P88-1020">
  <Title>Rhetorical Structure Theory: Description and Construction of Text Structures, in Natural Language Generation: Nero Results in</Title>
  <Section position="8" start_page="166" end_page="167" type="concl">
    <SectionTitle>
7 Shortcomings and Further
</SectionTitle>
    <Paragraph position="0"> Work This work is also being tested in a completely separate domain: the generation of text in a multi-media system that answers database queries. Penman produces the following description of the ship Knox (where CTG 070.10 designates a group of ships): (c). Knox is en route in order to rendenvous with CTG 070.10, arriving in Pearl Harbor on 4/24, for port visit until 4~so. In this text, each clause (en route, rendezvous, arrive, visit) is a separate input element; the structurer linked them using the relations Sequence and Purpose (the same Purpose as shown above; it is signalled by ~in order toN). However, Penman can also be made to produce (d). Knox is en route in order to rendezvous with CJTG 070.10. It w~11 arrive in Pearl Harbor on 4/24. It will be on port visit until 4/30.</Paragraph>
    <Paragraph position="1"> The problem is clear: how should sentences in the paragraph be scoped? At present, avoiding any claims about a theory, the structurer can feed  Penman either extreme: make everything one sentence, or make each input element a separate sentence. However, neither extreme is satisfactory; as is clear from paragraph (b), ashort&amp;quot; spans of text can be linked and &amp;quot;long&amp;quot; ones left separate. A simple way to implement this is to count the number of leaves under each branch (nucleus or satellite) in the paragraph structure tree.</Paragraph>
    <Paragraph position="2"> Another shortcoming is the treatment of input elements as indivisible entities. This shortcoming is a result of factoring out the problem of aggregation as a separate text planning task. Chunking together input elements (to eliminate detail) or taking them apart (to be more detailed) has received scant mention -- see \[Hovy 87\], and for the related problem of paraphrase see \[Schank 75\] -but this task should interact with text structuring in order to provide text that is both optimally detailed and coherent.</Paragraph>
    <Paragraph position="3"> At the present time, only about 20~ of the RST relations have been formalized to the extent that they can be used by the structurer. This formalization process is di~cult, because it goes hand-in-hand with the development of terms with which to characterize the relations' goals/constraPSuts. Though the formalization can never be completely finalized -- who can hope to represent something like motivation or justification complete with all ramifications? -- the hope is that, by having the requirements stated in rather basic terms, the relations will be easily adaptable to any new representation scheme and domain. (It should be noted, of course, that, to be useful, these formalizations need only be as specific and as detailed as the dom~in model and representation requires.) In addition, the availability of a set of communicative goals more detailed than just say or ask (for example), should make it easier for programs that require output text to interface with the generator. This is one focus of current text planning work at ISL</Paragraph>
  </Section>
class="xml-element"></Paper>