<?xml version="1.0" standalone="yes"?>
<Paper uid="A83-1031">
  <Title>INTERACTIVE NATURAL LANGUAGE PROBLEM SOLVING: A PRAGMATIC APPROACH</Title>
  <Section position="8" start_page="188" end_page="188" type="concl">
    <SectionTitle>
OTRER kK)RK
</SectionTitle>
    <Paragraph position="0"> Much of the applied work in natural language processing has concerned database query (Bronnenberg et al. C8\], CoddC9\], Harris\[17,18\], Hendrix\[22\], MylOpoUlOe\[27\], Plath\[29\], Thompson and Thompson\[32\], Weltz\[35\], and Woods et el.</Paragraph>
    <Paragraph position="1"> \[36\]). At least one such system is being marketed (namely INTELLECT \[18\]), while several others have been successfully used in pilot studies. (Damerau\[10\], F.~ly and Wescourt\[12\], Hershman et el. \[24\], Krause\[25\], Tennant\[31\]).</Paragraph>
    <Paragraph position="2"> As described in this paper, our initial work with N-LC involved programming as an application area, while our more recent interest has shifted toward office domains. However, as Petrick\[2R\] observes, many of the same technical problems arise regardless of application area. For the most part, the imperative sentence structures we are dealing with are simpler than the question forms recognized by the database systems cited above, while our noun phrases tend to exhibit more elaborate structures. Furthermore, whereas typical database sy-tems process each input separately, or perhaps seek to handle ellipsis by consulting the immedlately preceding input, we build up a richer semantic context as a session proceeds to be used in handling matters such as focus and pronoun resolution.</Paragraph>
    <Paragraph position="3"> The most distinctive features of our present work are (a) the inclusion of voice input and output facilities, and (b) an attempt to deal with relatively &amp;quot;deep&amp;quot; relationships among domain objects. A more detailed discussion of the domain-independent mechanisms appears in Biermann\[5\], and as described in Ballard \[2\] the related LDC project being conducted in our laboratory is built around many of these techniques. Similar research projects which are moving away from a fixed database setting include work by Haas and Hendrix\[16\], Reldorn\[20\], Hendrix and Lewis\[231, and Thompson and Thompson \[33\]. During the 197O's a number of speech understanding systems were developed under ARPA support (Lea \[26\], Reddy C30\], Walker \[34\], Woods \[37\]) and currently some systems ace being built in other countries, for example \[19\]. Rowever, none of these</Paragraph>
  </Section>
class="xml-element"></Paper>