Computer Generation Of Natural Language From A Deep Conceptual Base

For many tasks involving communication between humans and computers it is necessary for the machine to produce as well as understand natural language. We describe an implemented system which generates English sentences from Conceptual Dependency networks, which are unambiguous, language-free representations of meaning. The system is designed to be task independent, and thus capable of providing the language generation mechanism for such diverse problem areas as question answering, machine translation, and interviewing.

One of the aims of Natural Language Processing is to facilitate .the use of computers by allowing their users to communicate in natural language. There are two important aspects to person-machine communication: understanding and generating. While natural language understanding has been a major focus of research, natural language generation is a relatively new and increasingly active field of research. This book presents an overview of the state of the art in natural language generation, describing both new results and directions for new research. The principal emphasis of natural language generation is not only to facili tate the use of computers but also to develop a computational theory of human language ability. In doing so, it is a tool for extending, clarifying and verifying theories that have been put forth in linguistics, psychology and sociology about how people communicate. A natural language generator will typically have access to a large body of knowledge from which to select information to present to users as well as numer of expressing it. Generating a text can thus be seen as a problem of ous ways decision-making under multiple constraints: constraints from the propositional knowledge at hand, from the linguistic tools available, from the communicative goals and intentions to be achieved, from the audience the text is aimed at and from the situation and past discourse. Researchers in generation try to identify the factors involved in this process and determine how best to represent the factors and their dependencies.

Natural language generation is a field within artificial intelligence which looks ahead to the future when machines will communicate complex thoughts to their human users in a natural way. Generation systems supply the sophisticated knowledge about natural languages that must come into play when one needs to use wordings that will overpower techniques based only on symbolic string manipulation techniques. Topics covered in this volume include discourse theory, mechanical translation, deliberate writing, and revision. Natural Language Generation Systems contains contributions by leading researchers in the field. Chapters contain details of grammatical treatments and processing seldom reported on outside of full length monographs.

Fundamental Studies in Computer Science, 3: Conceptual Information Processing discusses a theory of natural language and implementation of that theory on a computer, focusing basically on an Artificial Intelligence approach to linguistics. This book aims to write computer programs that could understand and generate sentences, which is intended as a first step towards the long range goal of a computer that can communicate with people in natural language. The topics covered include computational linguistics, conceptual dependency theory, history of the analyzer, representation in memory, and structure of BABEL. This publication is a good reference for researchers and specialists working in the field of computer science.

On-line information -- and free text in particular -- has emerged as a major, yet unexploited, resource available in raw form. Available, but not accessible. The lexicon provides the major key for enabling accessibility to on-line text. The expert contributors to this book explore the range of possibilities for the generation of extensive lexicons. In so doing, they investigate the use of existing on-line dictionaries and thesauri, and explain how lexicons can be acquired from the corpus -- the text under investigation -- itself. Leading researchers in four related fields offer the latest investigations: computational linguists cover the natural language processing aspect; statisticians point out the issues involved in the use of massive data; experts discuss the limitations of current technology; and lexicographers share their experience in the design of the traditional dictionaries.