<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2122">
  <Title>A Case Study of Natural Language Customisation: The Practical Effects of World Knowledge</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 NLI and Sales Application
</SectionTitle>
    <Paragraph position="0"> The database was a large and complex on-line sales database, containing information about orders, deliveries, brands, customer preferences, sales territories, promotions and competitors. There were 20-30 different types of records with over 200 views ranging over data summaries of 2-3 years.</Paragraph>
    <Paragraph position="1"> Our user group consisted of 50 managers, composed of accounts, brands, commercial and marketing managers, each with different data requirements. They fit the user profile recommended for NLI's\[8\]. They were relatively infrequent computer users, who were experts in the domain with at least one year's experience. None knew anything about database languages.</Paragraph>
    <Paragraph position="2"> Some of them had used a previously installed NLI, Intellect, as well as a menu-based interface that accessed AcrEs DE COLING-92, NANTES, 23-28 AOt~n&amp;quot; 1992 8 2 0 PROC. OF COLING-92, NANTES, AUG. 23-28, 1992 tile name set of data 1. They required ad hoe access to information that was difficult to support with standard reports.</Paragraph>
    <Paragraph position="3"> The NLI we worked with was considered state of the art. It appeared to use a pipeline architecture consisting of morphological analysis, parser, semantic illterpretation, and database query translator. The semantic representation language was a hybrid of a semantic network and first order predicate logic, which supported time dependent facts, qnantified statements, tense information and general sets\[3\]. In addition, this NLI included a Generator that produced English from ttle semantic representation language, a Deductive Sys tern that reasoned about statements in the representation language using forward and backward chaining, and which handled quantification, time dependent facts and truth maintenance. Aruoug the knowledge sources that came with the NLI was a Dictionary of 10000 initial English words, and a set of Concepts that provided internal notions of predicates, and set and membership hierarchies.</Paragraph>
    <Paragraph position="4"> The semantic representation, concepts, and dictionary modules supported both intensional and extensional representation of data. In addition, users could add both new concepts and inference rules to tile sys tern with simple declarative sentences.</Paragraph>
  </Section>
class="xml-element"></Paper>