<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1048">
  <Title>Semantic Information Preprocessing for Natural Language Interfaces to Databases</Title>
  <Section position="6" start_page="315" end_page="315" type="concl">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"> Automating the process of finding selectional restrictions reduces NLI development time and may avoid errors introduced by hand-coding selectional restrictions. Althcugh the preprocessing is computationally intensive, it is done off-line during the delevopment of the NLI.</Paragraph>
    <Paragraph position="1"> A similar approach was proposed in (Alshawi, 1992) but a different method was suggested. (Alshawi, 1992) derives selectional restrictions from the types associated with the database predicates, whereas our approach uses only the constraints that the RLDT imposes on the input language.</Paragraph>
    <Paragraph position="2"> Future work will explore other uses of normalized RLDTs: to construct a sophisticated help system, to lexicalize some small database domains, and to develop more complex lexical entries. We shall also consider the possible uses of our work in general NLP.</Paragraph>
  </Section>
class="xml-element"></Paper>