<?xml version="1.0" standalone="yes"?>
<Paper uid="P84-1088">
  <Title>A Response to the Need for Summary Responses</Title>
  <Section position="2" start_page="0" end_page="432" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> For over a decade research has been ongoing into the diverse and complex issues involved in developing smart natural language interfaces to database systems.</Paragraph>
    <Paragraph position="1"> Pioneering front-end systems such as PLANES \[15\], REQUEST \[121, TORUS \[11\] and RENDEZVOUS \[1\] experimented with, among other things, various parsing formalisms (e.g. semantic grammars, transformational grammars and auglmented transition networks); the need for knowledge representation (e.g. using production systems or semantic networks); and the usefulness of clarification dialogue in disambiguating a user's query.</Paragraph>
    <Paragraph position="2"> Recent research has addressed various dialogue issues in order to enhance the elegance of the database interactions. Such research includes attempts to resolve anaphoric references in queries \[2,4,14,18\], to track the user's focus of attention \[2,4,14,18\], and to generate cooperative responses. In particular, the CO-OP system \[7\] is able to analyze presumptions of the user in order to generate appropriate explanations for answers that may mislead the user. Janas \[5\] takes a similar approach to generate indirect answers instead of providing direct inappropriate ones. Mays \[8\] has developed techniques to monitor changes in the data-base and provide relevant information on these changes to the user. McCoy \[9\] and McKeown \[10\] attempt to provide answers to questions about the structure of the database rather than extensional information as to its contents. We investigate herein, one particular approach to generating &amp;quot;non-extensional&amp;quot; responses - in particular the generation of &amp;quot;summary&amp;quot; responses. Generating abstract &amp;quot;summary&amp;quot; responses to users' queries is often preferable to providing enumerative replies. This follows from an important convention of human dialogue that no participant should monopolize the discourse (i.e. &amp;quot;be brief&amp;quot; \[3\]). Furthermore, extensional responses can occasionally mislead the user where summary responses would not. Consider the following example \[13\]: QI: Which department managers earn over $40k per year? SI-I: Abel, Baker, Charles, Doug.</Paragraph>
    <Paragraph position="3"> SI-2: All of them.</Paragraph>
    <Paragraph position="4"> By enumerating managers who earn over $40k, the fizst response implies that there are managers who do not earn that much. In linguistic pragmatics, this is called a scalar implicature \[3\]. In circumstances where the user is liable to infer an invalid scalar implicature, the system should be able to produce an appropriate response to block the generation of such an inference as is done by the response $1-2.</Paragraph>
    <Paragraph position="5"> 2. Overview of the System We describe herein a system which has been developed for the generation of summary responses to user's queries (fully detailed in \[6\]). The system arrives at concise responses by employing a search of the relevant data for the existence of &amp;quot;interesting&amp;quot; patterns. It uses heuristics to guide this search and a knowledge base to enhance efficiency and help determine &amp;quot;interestinguess&amp;quot;.</Paragraph>
    <Paragraph position="6"> The database used to test the system is a simple + Now, at the Department of Computer Science, University of Waterloo, Waterloo, Ontario, N2L 3G1, CANADA  relational database of student records, although the methods developed are largely domain-independent. In order to concentrate on the response generation issues, the input/output for the system is in an internal form an actual parser and surface language generation capabilities will be incorporated in future versions of the system.</Paragraph>
    <Paragraph position="7"> The flow of control in the system is simple. The formal representation of the query is used to access the database and obtain the tuples which satisfy the user's query {which we will call T~; the other tuples will be called Tu,~,~). After the data is accessed, the system, in consultation with its knowledge base, calls upon its heuristics to find interesting non-enumerative patterns. The heuristics are tried in order, until one succeeds or all fail. When a heuristic detects an appropriate pattern, the system terminates the search and produces the response as dictated by the successful heuristic. If all heuristics fail, the system reports its inability to produce a descriptive response. In any event, the user may ask the system to produce an extensional answer by listing the data if he/she so desires.</Paragraph>
  </Section>
class="xml-element"></Paper>