<?xml version="1.0" standalone="yes"?>
<Paper uid="C86-1130">
  <Title>Knowledge Structures for Natural Language Generatlon ~</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The task of natural language generation is that of producing linguistic output to satisfy the communicative requirements of a computer system. The principal limitation of existing programs which perform this function is that they fail to realize a sufficiently broad range of requirements to demonstrate a convincing linguistic capability. This drawback seems founded in aspects of the systems which hinder the development of a large base of knowledge about language. A great deal of knowledge is required to produce any given utterance, yet much of this knowledge cannot easily be exploited across a range of utterances.</Paragraph>
    <Paragraph position="1"> Partial success in generation systems is often achieved by applying linguistic knowledge to particular domains. Exemplary of this success are text generation programs such as PROTEUS \[6\], and Ann \[15,14\]; as well as generation components of on-line systems; for example, in HAM-ANS \[5\], UC \[9,11\[, and VIE-LANG \[4 I. These systems, while embodying a variety of generation techniques, serve to illustrate the importance of the command of specialized constructs and the ability to utilize specialized knowledge in generation. A close examination of the knowledge used in such programs, however, reveals that a great deal of linguistic information seems to be encoded redundantly, thus impeding the use of generalizations in &amp;quot;scaling up ~ the systems.</Paragraph>
    <Paragraph position="2"> The UNIX 2 Consultant system \[22\] is a program which answers questions from naive users about the UNIX operating system. Scaling up the user interface required a generator which could produce responses such as the following:  1. 'Chmod' can be used to give you write permission.</Paragraph>
    <Paragraph position="3"> 2. You don't have write permission on the directory.</Paragraph>
    <Paragraph position="4"> 3. You can't get write permission on the directory.</Paragraph>
    <Paragraph position="5"> 4. You need ethernet access.</Paragraph>
    <Paragraph position="6">  'This paper is based on the thesis research conducted while the au- thor was at the University of California, Berkeley. The research was supported in part by the Office of Naval Research under con- tract N00014-80-C-0732, the National Science Foundation under grants IST-8007045 and IST-8208602, and the Defense Advanced Research Projects Agency (DO D), ARPA Order No. 3041, Monitored by the Naval Electronic Systcras Command under contract N00039-82-C-0235.</Paragraph>
    <Paragraph position="7"> 5. You don't have ethernet access.</Paragraph>
    <Paragraph position="8"> The PHRED generator initially used by UC \[11\] produced output such as the above by treating each verb use as an independent specialized construct. This allowed no benefit to the system of abstract knowledge about the use of the verbs, nor of applying its knowledge about one specialized construct to another. This difficulty proves to be a major handicap in building large-scale generation systems: A key element is to facilitate the exploitation of generalizations while still providing for specialized uses. In order for the UC system to have this capacity, the linguistic knowledge representation used had to be redesigned.</Paragraph>
    <Paragraph position="9"> This knowledge-based approach has led to the design and implementation of the Ace knowledge representation framework \[12\]. Ace is a uniform, hierarchical representation system, which facilitates the use of abstractions in the encoding of specialized knowledge as well as the representation of referential and metaphorical relationships among concepts. A general-purpose natural language generator, KING (Knowledge INtensive Generator)f10\], has been implemented to apply knowledge in the Ace form. The generator works by applying structured associations, or mappings, from conceptual to linguistic structures, and combining these structures into grammatical utterances. This has proven to be a simple but powerful mechanism, easy to adapt and extend, and has provided strong support for the use of Ace knowledge structures in generation.</Paragraph>
    <Paragraph position="10"> While this presentation describes the Ace knowledge struc- tures from the point of view of language production, the representation framework is designed to be unbiased with respect to language analysis or generation. The discussion which follows focuses on the representation of linguistic and conceptual knowledge in Ace, using as an example knowledge about the verbs &amp;quot;give &amp;quot;, &amp;quot;take &amp;quot;, &amp;quot;buy&amp;quot; and &amp;quot;sell &amp;quot;. The examples show briefly how information is encoded in Ace which enables the generator to produce dative constructs such as &amp;quot;John sold Mary a book ~ and specialized forms such as &amp;quot;John gave Mary a kiss&amp;quot;, making use of abstract knowledge about events such as giving. These verbs provide a good testing ground for a representational framework, as they may be characterized by certain linguistic generalizations while appearing in a variety of specialized constructs. For further examples and a description of the generation algorithm used by KING, the reader is referred to \[10\].</Paragraph>
  </Section>
class="xml-element"></Paper>