<?xml version="1.0" standalone="yes"?>
<Paper uid="P85-1031">
  <Title>AN ECLECTIC APPROACH TO BUILDING NATURAL LANGUAGE INTERFACES</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The ides/ natural language interface would let any user, without any prior training, interact with a computer. Such an interface would be useful in the knowledge acquisition phase of expert system development where the diagnostic knowledge of a Hilled practitioner has to be elicited. As technicians are not farnifiar with formal knowledge representation schemes, a trained intermediary, a knowledge engineer, is generally employed to handcraft the interns/ format. This process is time-consuming and expensive.</Paragraph>
    <Paragraph position="1"> INKA (INglish Knowledge Acquisition) permits task experts to express their knowledge in a subset of English, and have it automatically translated into the appropriate representational formalism. In particular, the version of INKA to be discussed here accepts input in a sublanguage called GLIB which permits the statement of facts and rules relevant to the troubleshooting of electronic systems (Freiling et al., 1984), and translates these statements into Prolog unit clauses for later proce~ng by a specialized inference mechanism. Experiments with INKA to date have enabled us to construct mfflcient troubleshooting rules to build a localizing troubleshooter for a simple circuit.</Paragraph>
    <Paragraph position="2"> INKA is designed as one of the tools of DETEKTR, an environment for building knowledge based electronic instru.</Paragraph>
    <Paragraph position="3"> ment troubleshooters (Freiling &amp; Alexander, 1984).</Paragraph>
    <Paragraph position="4"> DETEKTR supports an expert system development methodology which is outlined below. The design goal of INKA is that it serve as a natural language input system to facilitate transfer of knowledge during the knowledge acquisition phase of expert system development. IIqKA is not intended to stand alone as the sole mechanism for knowledge transfer, but to be supt A summer intern at Tektronix, currently at the University of llfinois, Champs/gn-Urbana.</Paragraph>
    <Paragraph position="5"> ported by components capable of managing a coherent dis/ogue with the task expert. McKeown (1984) has po/nted out a number of important aspec~ of the pragmatics that relate to the usage phase of an expert system. Similar pragmatics are required to insure adequate construction of the system's knowledge base during the knowledge ac~n phase of an expert system's development. The most important pragmatic facility is one to estimate the degree of epistemiC/ coverage of the knowledge acquired so far, and to prompt the task expert for more knowledge in areas where the coverage is weak. It is unfeasible to assume that any task expert can simply perform a ~memory dump&amp;quot; of expertise into some natural language interface and be done with it.</Paragraph>
    <Paragraph position="6"> This paper discusses the natural language technology used in building INKA. The system incorporates a diverse collection of natural language technologies in its construction. Specifically, INKA utilizes a semam/c grammar (Burton, 1976) to characterize the domain sublanguage, lexical-functional sem~aics (Kaplan &amp; Bresnan, 1982) to translate to the internal form of representation, and an interface that includes left-corner parsitlg with in-line guidance to address the Linguistic coverage problem that aris~ with sublanguages. We feel this eclectic approach is a useful for building application-oriented natural language interfaces. Although we are describing a knowledge acquisition application, the methodology can be used for any application whose sublanguage can be stated in the prescribed grammar formalism.</Paragraph>
    <Paragraph position="7"> Tereisias (Davis, 1977) provides a natural language environment for debugging a knowledge base. INKA at present contains no facilities to modify an existing rule or to test the evolving knowledge base for some level of integr/ty; these are to be future additions.</Paragraph>
    <Paragraph position="8"> INKA is written in Smalltalk (Goidberg &amp; Robson, 1983) and runs on both the Tekuroulx Magnolia Workstation and the 4404 Artificial Intelligence System. INKA makes extensive use of the bit-mapped display and three-button mouse on these systems.</Paragraph>
  </Section>
class="xml-element"></Paper>