Browse Prior Art Database

Two Types of Planning in Language Generation

IP.com Disclosure Number: IPCOM000128687D
Original Publication Date: 1988-Dec-31
Included in the Prior Art Database: 2005-Sep-16
Document File: 11 page(s) / 42K

Publishing Venue

Software Patent Institute

Related People

Eduard H. Hovy: AUTHOR [+3]

Abstract

PAULINE (Planning And Uttering Language In Natural Environments) is a language gener-ation program that is able to realize a given input in a number of different ways, depending on how its pragmatic (interpersonal and situation-specific) goals are set by the user. The program consists of over 12,000 lines of T, a dialect of LISP developed at Yale University. PAULINE addresses simultaneously a wider range of problems than has been tried in any single language generation program before (with the possible exception of (Clippinger 74l). As is to be expected, no part of PAULINE provides a satisfactorily detailed solution to any problem; to a larger or smaller degree, each of the questions it addresses is solved by a set of simplified, somewhat ad hoc methods. However, this is not to say that the program does not provide some interesting insights about the nature of language generation and the way that generators of the future will have to be structured. One insight pertains to the problems encountered when the various tasks of generation -both of text planning and of realization - are interleaved to provide planning-on-demand rather than strict top-down planning (which has been the approach taken so far). The planning tasks that are best performed on demand tend to have short-range effects on the text (compared to those best performed in full before realization). In order to achieve the types of communicative goals such tasks usually serve; the planner must ensure that they work together harmoniously so that their effects support one another rather than conflict. This requirement imposes constraints on the organization and architecture of a generation system. This paper describes PAULINE's architecture, the text planning tasks implemented, and how the tasks are managed. Unfortunately many details have to be left unsaid; the in-terested reader is referred to relevant material at appropriate points. Overview descriptions appear in (Hovy 87a, 87b).

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 9% of the total text.

Page 1 of 11

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

Two Types of Planning in Language Generation

Eduard H. Hovy

ISI Reprint Series ISIIRS-88-209 April 1988 University of Southern California Reprinted from Proceedings of the 26th Meeting of the A CL, Buffalo, New York, 1988. INFORMATION SCIENCES INSTITUTE 213/822-1511 9676 Admiralty Way/Marina del Rey/California 90292- 6695 This research was supported in part by the Defense Advanced Research Projects Agency monitored by the Office of Naval Research under Contract No. N00014-82-K-0149, and in part by AFOSR Contract No. F49620-87-C-0005. Any opinions, conclusions or recommendations expressed in this publication are those of the author and should not be interpreted as representing the official opinion of DARPA, ONR, AFOSR, or any person or agency connected with them.

ISI Reprint Series This report is one in a series of reprints of articles and papers written by ISI research staff and published in professional journals and conference proceedings. For a complete list of ISI reports, write to

Document Distribution USC/Information Sciences Institute

4676 Admiralty Way Marina del Rey, CA 90292-6695 USA

1 Introduction

PAULINE (Planning And Uttering Language In Natural Environments) is a language gener-ation program that is able to realize a given input in a number of different ways, depending on how its pragmatic (interpersonal and situation-specific) goals are set by the user. The program consists of over 12,000 lines of T, a dialect of LISP developed at Yale University.

PAULINE addresses simultaneously a wider range of problems than has been tried in any single language generation program before (with the possible exception of (Clippinger 74l). As is to be expected, no part of PAULINE provides a satisfactorily detailed solution to any problem; to a larger or smaller degree, each of the questions it addresses is solved by a set of simplified, somewhat ad hoc methods. However, this is not to say that the program does not provide some interesting insights about the nature of language generation and the way that generators of the future will have to be structured.

One insight pertains to the problems encountered when the various tasks of generation -both of text planning and of realization - are interleaved to provide planning-on-demand rather than strict top-down planning (which has been the approach taken so far). The planning tasks that are best performed on demand tend to have short-range effects on the text (compared to those best performed in full before realization). In order to achieve the types of communicative goals such tasks usually serve; the planner must ensure that they work together harmoniously so that their effects support one another rather than conflict. This requirement imposes constraints on the organization and architecture of a generation system.

This paper describes PAULINE's architecture, the text planning tasks implemented, and how the tasks are managed...