<?xml version="1.0" standalone="yes"?>
<Paper uid="W94-0307">
  <Title>Content and Rhetorical Status Selection in Instructional Texts</Title>
  <Section position="2" start_page="0" end_page="53" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A standard problem in text generation is to determine what to include in the text and how to structure it. The goal of this research is to study how the content of instructional texts and their rhetorical structure can be selected automatically. The approach taken starts from a task representation developed by an AI planner, from which a set of semantic carriers, specifying the content of the text, is selected. Then the rhetorical relations that best communicate these semantic carriers are selected. The approach is based on a corpus analysis that determined: * What semantic carriers are found in instructional texts, where they can be found in the task representation and when they are included in the text.</Paragraph>
    <Paragraph position="1"> * What rhetorical relations are used to present the semantic carriers and when one is preferred over another. null If these points are not dealt with, an instructional text generator may choose to say everything available in the task representation, and may communicate it using always the same rhetorical strategy. For example, the task of using the one touch record (OTR) feature of a VCR can be represented as in figure 11 . From this task representation, the following unacceptable text may be produced: To use the 0TR feature, set the speed selector to &amp;quot;SP&amp;quot;, &amp;quot;SP&amp;quot; will light up; select channel 4; specify the recording time; emd press the TIMER button within 9 seconds, the TIMER indicator wPS11 light up.</Paragraph>
    <Paragraph position="2"> To set the speed selector to deg*SP&amp;quot;, press the SP/EP button. The speed will change.</Paragraph>
    <Paragraph position="3"> To set channel 4, press the channel button. The channel will change.</Paragraph>
    <Paragraph position="4"> To specify the recording time, press the OTR button 3 times.</Paragraph>
    <Paragraph position="5"> To press the OTR button 3 times, press it once, PM 10:35; press it a second time, PM 11:05; press it a third time, PM 11:35.</Paragraph>
    <Paragraph position="6"> A more natural text would be~: The 0TR feature: Set the tape speed selector to &amp;quot;SP&amp;quot;. &amp;quot;SP&amp;quot; will (I) light up.</Paragraph>
    <Paragraph position="7"> Select channel 4, by pressing the channel button. (2) Press the OTR button 3 times to specify the (3) recording time.</Paragraph>
    <Paragraph position="8"> When the button is pressed once, PM 10:35. (4) When it is pressed twice, PM 11:05. (5) When it is pressed 3 times, PM 11:35. (6) Press the TIMER button within 9 seconds. The (7) TIMER indicator will light up.</Paragraph>
    <Paragraph position="9"> Not all the knowledge of the task representation is introduced in the text. For example, many parent-child relations between operations are left unsaid. In addition, the same type of knowledge is not always presented by the same rhetorical relation. For example the parent-child relation of the operations in sentence (2) is expressed by an enabiement relation rather than a purpose as in sentence (3).</Paragraph>
    <Paragraph position="10"> The paper first reviews previous work in instructional text planning. The results of the corpus analysis leading lIn figure 1, operations are indicated on the top lines and post-conditions are preceded by an &amp;quot;=./'.</Paragraph>
    <Paragraph position="12"> to the development of the planning approach are then discussed. Finally, preliminary results of a prototype system are presented.</Paragraph>
  </Section>
class="xml-element"></Paper>