Machine Learning of Natural Language

David M. W. Powers

ISBN 10: 3540195572 / ISBN 13: 9783540195573

Editore: Springer, Springer, 1989

Riguardo questo articolo

Druck auf Anfrage Neuware - Printed after ordering - We met because we both share the same views of language. Language is a living organism, produced by neural mechanisms relating in large numbers as a society. Language exists between minds, as a way of communicating between them, not as an autonomous process. The logical 'rules' seem to us an epiphe nomena of the neural mechanism, rather than an essential component in language. This view of language has been advocated by an increasing number of workers, as the view that language is simply a collection of logical rules has had less and less success. People like Yorick Wilks have been able to show in paper after paper that almost any rule which can be devised can be shown to have exceptions. The meaning does not lie in the rules. David Powers is a teacher of computer science. Christopher Turk, like many workers who have come into the field of AI (Artificial Intelligence) was originally trained in literature. He moved into linguistics, and then into computational linguistics. In 1983 he took a sabbatical in Roger Shank's AI project in the Computer Science Department at Yale University. Like an earlier visitor to the project, John Searle from California, Christopher Turk was increasingly uneasy at the view of language which was used at Yale.; We are still a long way from designing computers that can understand human languages. The authors view natural language as fundamental to human cognitive processes and perhaps the key to making machines that can understand us. In this electronic age, language is increasingly the province of workers in the fields of cognitive psychology and artificial intelligence who record, transmit, simulate and analyse its form and representation. The authors explore current thinking in the search for machine understanding of human languages, focusing on how computing machinery can acquire the cognitive structures which occur in natural language. The book begins with a summary of basic views of methodology, bringing together linguistic, scientific, neurological and related cognitive approaches. It concludes with a description of experimental learning mechanisms, some of which are simplifications of the way a natural language acquisition system might be built, and some example programs in PROLOG. Die Autoren erforschen aktuelle Denkrichtungen, die das Ziel haben, daß Maschinen natürliche Sprachen verstehen. Zunächst wird eine Zusammenfassung der grundlegenden Methodik gegeben; am Schluß werden experimentelle Lernmechanismen und Beispielprogramme in PROLOG beschrieben.

Codice articolo 9783540195573

Dati bibliografici

• Titolo: Machine Learning of Natural Language
• Editore: Springer, Springer
• Data di pubblicazione: 1989
• Lingua: Inglese
• ISBN 10: 3540195572
• ISBN 13: 9783540195573
• Rilegatura: Taschenbuch
• Condizione: Neu
• Dimensioni: 242 L x 170 A x 21 P (millimetri) 242 millimetri di larghezza per 170 millimetri di altezza per 21 millimetri di profondità
• Peso: 636 grammi

Descrizione articolo

Riassunto

We are still a long way from designing computers that can understand human languages. The authors view natural language as fundamental to human cognitive processes and perhaps the key to making machines that can understand us. In this electronic age, language is increasingly the province of workers in the fields of cognitive psychology and artificial intelligence who record, transmit, simulate and analyse its form and representation. The authors explore current thinking in the search for machine understanding of human languages, focusing on how computing machinery can acquire the cognitive structures which occur in natural language. The book begins with a summary of basic views of methodology, bringing together linguistic, scientific, neurological and related cognitive approaches. It concludes with a description of experimental learning mechanisms, some of which are simplifications of the way a natural language acquisition system might be built, and some example programs in PROLOG.

Contenuti

1 Art, Science and Engineering.- Cognitive Structures.- Scientific Method.- Language is Contrastive.- 2 Metaphor as a Cognitive Process.- Conjecture and Refutation, Theories and Hypotheses.- Specialization and Abstraction, Induction and Generalization.- Partial Analysis and Noise.- The Importance of Errors and Restrictions.- 3 Psychology and Psycholinguistics.- The Observable Processes of Acquisition.- External Influences: Parents, Imitation, and Correction.- Expansion and Reduction.- 4 Language Defects and Correction.- Rate and Order of Learning.- Telegraphic Speech.- Parents and Teachers: Good and Bad Examples.- Reinforcement: Punishment and Reward.- 5 Cognition and Restriction.- The Cognitive Processes of Language Acquisition.- The Magical Number Seven.- Memory and Capacity Phenomena.- Adult Characteristics.- 6 Nativism and Constructivism.- Representations: Deep Structure and Language Acquisition.- Acquisition Models, Chomsky and Piaget.- Computer Programs as Psychological Models.- 7 Neurology and Neurolinguistics.- Neuroanatomy: Brains, Neurons, and Synapses.- Neurophysiology and the Effects of Plasticity.- Neural Communication and Languages of the Brain.- Neural Nets: Connectionistic and Locationistic Models.- 8 The Nature of Language.- The Quintessence of Language.- Epistemology, Phonology, and Prosody.- Culture, Perspectives, and Metaphor.- 9 The Mechanics of Language.- Contrast and Similarity: Paradigmatic Learning and Context.- The Structures of Language.- Models of Grammar.- 10 The Ubiquity of the Sentence.- Pronouns and Anaphora.- Recursion of Syntax and Parsing.- Transformational Grammar.- Generative Grammar.- Learning Process and Idiolect.- 11 Computer Science and Artificial Intelligence.- Pattern Recognition, Problem Solving and Heuristic Search.- Learning Strategies.- Problems and Theoretical Limitations.- 12 Heuristics and Analytic Intransigence.- Automata and Formal Languages.- Methodologies: Implementation vs Experimentation.- Cybernetics and Robotics.- Deletionless Strategies.- Formalisms.- Clauses: Horn and non-Horn, unit and non-unit Systems: LUSH and PROLOG.- 13 Postulates, Claims and Hypotheses.- The Bases of Meaning and Learning.- The Organization of Concepts in Learning.- The Process of Learning.- The Artificial Subsumes the Natural.- 14 Computer Modelling Experiments.- Batteries One to Seven.- A Generalized Toy World Package.- Partial Analysis of NLA.- Future Systems.- Conclusions.