Discourse Strategies for Generating Natural-Language Text

I f a generation system is to produce text in response to a given communicative goal, it must be able to determine what to include in its text and how to organize this information so that it can be easily understood. In this paper, a computational model of discourse strategies is presented that can be used to guide the generation process in its decisions about what to say next. The model is based on an analysis of naturally occurring texts and represents strategies that can be used for three communicative goals: deft ne, compare, and describe. We show how this model has been implemented in TEXT, a system which generates paragraph-length responses to questions about database structure.

[1]  H. B. Allen,et al.  A Functional Grammar , 1946 .

[2]  Lavinia P. Dudley The encyclopedia Americana , 1954 .

[3]  William A. Woods,et al.  Computational Linguistics Transition Network Grammars for Natural Language Analysis , 2022 .

[4]  Robert F. Simmons,et al.  Generating English discourse from semantic networks , 1972, CACM.

[5]  A. Malhotra Design criteria for a knowledge-based English language system for management : an experimental analysis , 1975 .

[6]  D. Bobrow,et al.  Representation and Understanding: Studies in Cognitive Science , 1975 .

[7]  D. Rumelhart NOTES ON A SCHEMA FOR STORIES , 1975 .

[8]  Peter P. Chen The Entity-Relationship Model: Towards a unified view of Data , 1976 .

[9]  Robert C. Moore Reasoning About Knowledge and Action , 1977, IJCAI.

[10]  James R. Meehan,et al.  TALE-SPIN, An Interactive Program that Writes Stories , 1977, IJCAI.

[11]  Wallace L. Chafe,et al.  The flow of thought and the flow of language , 1977 .

[12]  Philip R. Cohen On knowing what to say: planning speech acts. , 1978 .

[13]  E. F. Codd,et al.  RENDEZVOUS Version 1: An Experimental English Language Query Formulation System for Casual Users of Relational Data Bases , 1978, Research Report / RJ / IBM / San Jose, California.

[14]  Elaine Rich,et al.  User Modeling via Stereotypes , 1998, Cogn. Sci..

[15]  Ralph Grishman Response Generation in Question - Answering Systems , 1979, ACL.

[16]  Harry R. Tennant Experience with the Evaluation of Natural Language Question Answerers , 1979, IJCAI.

[17]  Candace L. Sidner,et al.  Towards a computational theory of definite anaphora comprehension in English discourse , 1979 .

[18]  Jerry R. Hobbs Coherence and Coreference , 1979, Cogn. Sci..

[19]  C. Raymond Perrault,et al.  Analyzing Intention in Utterances , 1986, Artif. Intell..

[20]  David D. McDonald Natural language production as a process of decision-making under constraints , 1980 .

[21]  J. L. Weiner,et al.  BLAH, A System Which Explains its Reasoning , 1980, Artif. Intell..

[22]  Douglas Edmund Appelt,et al.  Planning natural language utterances to satisfy multiple goals , 1981 .

[23]  William C. Mann,et al.  Computer Generation of Multiparagraph English Text , 1981, Am. J. Comput. Linguistics.

[24]  Scott Weinstein,et al.  Control of Inference: Role of Some Aspects of Discourse Structure-Centering , 1981, IJCAI.

[25]  W. R. Swartout PRODUCING EXPLANATIONS AND JUSTIFICATIONS OF EXPERT CONSULTING PROGRAMS , 1981 .

[26]  Robert Wilensky A Knowledge-Based Approach to Language Processing: A Progress Report , 1981, IJCAI.

[27]  Christian M. I. M. Matthiessen A Grammar and a Lexicon for a Text-Production System , 1981, ACL.

[28]  Terry Winograd,et al.  Language as a cognitive process 1: Syntax , 1982 .

[29]  Kathleen McKeown Focus Constraints on Language Generation , 1983, IJCAI.

[30]  William C. Mann An Overview of the Nigel Text Generation Grammar , 1983, ACL.

[31]  Cecile L. Paris,et al.  Determining the Level of Expertise of a User of a Question Answering System , 1984 .

[32]  Herbert H. Clark,et al.  DISCOURSE IN PRODUCTION , 1994 .