A new level of language generation technology: capabilities and possibilities
IEEE ExpertPublished 1 April 1992
Eduard Hovy
Citations3
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Penman, one of several general-purpose single-sentence generators that are gradually evolving toward full-scale commercial strength, is discussed.
Abstract
The different tasks and types of language generation systems are discussed. There are four types of generation systems: canned-text, template, phrase-based, and feature-based systems. Canned text is the simplest way of producing output and is used in the vast majority of software. Templates, the next level of sophistication, are used when a single message must be produced multiple times with slight alterations. Phrases are generalized templates and can be developed to considerable complexity. Features are the limit point of phrase generalization. Each possible minimal alternative of expression is represented by a single feature. These systems can be applied to produce multiparagraph texts, summaries of numerical information, explanations, help systems, multimedia interfaces, software documentation and machine translation. Penman, one of several general-purpose single-sentence generators that are gradually evolving toward full-scale commercial strength, is discussed.>
Keywords
Computer Science
Language<b>Introduction to functional grammar</b> . By M. A. K. Halliday London & Baltimore: Edward Arnold, 1985. Pp. xxxv, 387.
9,924 Citations1989Christian M.I.M. Matthiessen
Cognitive PsychologyUnderstanding natural language
2,802 Citations1972Terry Winograd
A computer system for understanding English that contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system based on the belief that in modeling language understanding, it must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference.
RHETORICAL STRUCTURE THEORY: A THEORY OF TEXT ORGANIZATION
894 Citations1987William C. Mann
This paper establishes a new definitional foundation for RST, Definitions are made more systematic and explicit, they introduce a new functional element, and incidentally reflect more experience in text analysis.
Artificial IntelligenceXPLAIN: a system for creating and explaining expert consulting programs
385 Citations1983William Swartout
The XPLAIN system uses an automatic programmer to generate a consulting program by refinement from abstract goals and provides justifications of the code by examining the refinement structure created by the automatic programmer.
IEEE Transactions on Software EngineeringA 15 Year Perspective on Automatic Programming
366 Citations1985Rosana Balzer
Automatic programming consists not only of an automatic compiler, but also some Means of acquiring the high-level specification to be compiled, some means of determining that it is the intended specification, and some (interactive) means of translating this high- level specification into a lower-level one which can be automatically compiled.
The MIT Press eBooksComputational Models of Discourse
344 Citations1983
A fundamental change is taking place in the study of computational linguistics analogous to that which has taken place in the study of computer vision over the past few years and indicative of trends that are likely to affect future work in artificial intelligence generally.
Journal of PragmaticsGenerating natural language under pragmatic constraints
340 Citations1987Eduard Hovy
IEEE ExpertExplanations in knowledge systems: design for explainable expert systems
194 Citations1991William Swartout, Cécile Paris +1 more
The explainable expert systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of the system's actions, explications of general problem-solving strategies, and descriptions of the systems' terminology, is discussed.
Planning coherent multisentential text
186 Citations1988Eduard Hovy
A set of 20 relations that span most of what people usually say in English is proposed in the Rhetorical Structure Theory of Mann and Thompson and used in a prototype text planner that structures input elements into coherent paragraphs.
Machine Translation: A Knowledge-Based Approach
130 Citations1992Sergei Nirenburg, Jaime Carbonell +2 more
The authors introduce the general paradigm of knowledge-based MT, survey major recent developments, compare it with other approaches and present a paradigmatic view of its component processes-natural language analysis, natural language generation, text meaning representation, ontological modeling, etc.
Columbia Academic Commons (Columbia University)Tailoring Explanations for the User
112 Citations1985Kathleen McKeown, Myron Wish +1 more
A method is presented for representing the knowledge to support different points of view in the current domain and a method for determining the point of view to take by inferring the user's goal within a brief discourse segment.
A flexible interface for linking applications to Penman's sentence generator
109 Citations1989Robert Kasper
Penman's interface with applications is described, focusing on SPL, a newly developed sentence plan language that can be used by text planning programs to specify plans for sentences at multiple levels of abstraction and varied amounts of detail.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Nigel: A Systemic Grammar for Text Generation.
100 Citations1983William C. Mann, Christian M.I.M. Matthiessen
The report consists of three papers on Nigel: an introductory overview, the script of a demonstration of its use in generation, and an exposition of how Nigel relates to the systemic framework.
The MIT Press eBooksNatural Language Generation as a Computational Problem: An Introduction
98 Citations1983
This chapter contains sections titled: Introduction, Results for Test Speakers, A Computational Model, The Relationship Between the Speaker and the Linguistics Component, The Internal Structure of the L linguistic Component, An Example, Contributions and Limitations.
Phrasing a text in terms the user can understand
85 Citations1989John Bateman, Cécile Paris
This research proposes a new mechanism which allows the text planning process to specifically tailor syntactic phrasing to the hearer type in the context of an expert system explanation facility that needs to produce explanations of the expert system's behavior for a variety of different users.
Columbia Academic Commons (Columbia University)The Use of Explicit User Models in Text Generation: Tailoring to a User's Level of Expertise
65 Citations1987Cécile Paris
TAILOR is shown how it can use information about a user's level of expertise to combine several discourse strategies in a single text, choosing the most appropriate at each point in the generation process, in order to generate texts for users anywhere along the knowledge spectrum.
National Conference on Artificial IntelligenceAutomatic construction of user-interface displays
52 Citations1988Yigal Arens, Lawrence H. Miller +2 more
This paper shows how Artificial Intelligence knowledge base and rule technology can be used to address the problem of construction of user interfaces when the user interface system must dynamically create displays integrating the use of several interfaces.
ACM SIGCHI BulletinIntelligent Multi-Media Interface Technology
25 Citations1988Jeannette G. Neal, Stuart C. Shapiro
A strategy to bring dialogue-like structure to user-system interaction is described, based on explicitly representing the "plans" of programs, and introducing those plans explicitly into the interface.
Functional unification grammar revisited
21 Citations1987Kathleen McKeown, Cécile Paris
It is shown that one benefit of FUG, the ability to state global constraints on choice separately from syntactic rules, is difficult in generation systems based on augmented context free grammars (e.g., Definite Clause Grammars).
Machine TranslationIntegrating discourse pragmatics and propositional knowledge for multilingual natural language processing
8 Citations1987Sergei Nirenburg, Jaime Carbonell
An integrated knowledge representation system for natural language processing (NLP) whose main distinguishing feature is its emphasis on encoding not only the usual propositional structure of the utterances in the input text, but also capturing an entire complex of nonpropositional meanings that NL texts always carry.
Intelligent Multi-Media Integrated Interface Project
8 Citations1990Jeannette G. Neal, Stewart Shapiro +3 more
A knowledge based multi media interface system, called CUBICON (the CUBRIC Intelligent CONversationalist), has been developed as a proof-of- concept prototype and is described in this report.
Machine translation again?
1 Citations1990Yorick Wilks, Jaime Carbonell +3 more
It is maintained that the most profitable approach to MT at the present time is an interlingual and modular one.