Muutke küpsiste eelistusi

E-raamat: Connectionist Approaches to Natural Language Processing

Edited by , Edited by
  • Formaat - EPUB+DRM
  • Hind: 54,59 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Originally published in 1992, when connectionist natural language processing (CNLP) was a new and burgeoning research area, this book represented a timely assessment of the state of the art in the field. It includes contributions from some of the best known researchers in CNLP and covers a wide range of topics.

The book comprises four main sections dealing with connectionist approaches to semantics, syntax, the debate on representational adequacy, and connectionist models of psycholinguistic processes. The semantics and syntax sections deal with a variety of approaches to issues in these traditional linguistic domains, covering the spectrum from pure connectionist approaches to hybrid models employing a mixture of connectionist and classical AI techniques.

The debate on the fundamental suitability of connectionist architectures for dealing with natural language processing is the focus of the section on representational adequacy. The chapters in this section represent a range of positions on the issue, from the view that connectionist models are intrinsically unsuitable for all but the associationistic aspects of natural language, to the other extreme which holds that the classical conception of representation can be dispensed with altogether.

The final section of the book focuses on the application of connectionist models to the study of psycholinguistic processes. This section is perhaps the most varied, covering topics from speech perception and speech production, to attentional deficits in reading. An introduction is provided at the beginning of each section which highlights the main issues relating to the section topic and puts the constituent chapters into a wider context.
List of Contributors
xii
Preface xiv
1 Connectionist Natural Language Processing
1(14)
Noel E. Sharkey
Ronan Reilly
Introduction
1(4)
Overview of chapters
5(4)
Acknowledgements
9(1)
References
9(6)
PART I SEMANTICS
Introduction
15(6)
2 Distributed Symbol Discovery through Symbol Recirculation: Toward Natural Language Processing in Distributed Connectionist Networks
21(28)
Michael G. Dyer
Margot Flowers
Yih-Jih Alan Wang
Introduction
21(1)
Natural language processing: Constraints from the task domain
22(3)
Dynamic vs. static symbol representations
25(2)
Symbol recirculation
27(2)
Encoding semantic networks in DUAL: A distributed connectionist architecture
29(9)
Other symbol recirculation methods
38(2)
Open problems
40(4)
Variable binding research and symbol formation
44(1)
Summary and conclusions
45(1)
Acknowledgements
45(1)
References
45(4)
3 Representing Meaning Using Microfeatures
49(26)
Richard F.E. Sutcliffe
Introduction
49(2)
Microfeature representations in PARROT
51(6)
Implementation of the microfeature concept within PARROT
57(5)
Examples
62(1)
Discussion and next steps
62(5)
Acknowledgements
67(1)
References
67(1)
Appendix I Outline of the PARROT system
68(2)
Appendix II Example entries from the lexicon
70(5)
4 Noun Phrase Analysis with Connectionist Networks
75(22)
Stefan Wermter
Wendy G. Lehnert
Introduction
75(1)
The domain
76(3)
Learning level: Learning semantic prepositional relationships
79(5)
Integration level: Integration of semantic and syntactic constraints
84(3)
A case study for the disambiguation of noun phrases
87(3)
Discussion
90(3)
Conclusion
93(1)
Acknowledgements
93(1)
References
93(4)
5 Parallel Constraint Satisfaction as a Comprehension Mechanism
97(42)
Mark F. St. John
James L. McClelland
Introduction
97(2)
Sentence comprehension
99(20)
Story comprehension
119(14)
Conclusions
133(1)
Acknowledgements
134(1)
References
134(2)
Appendix I Input and output representations
136(3)
PART II SYNTAX
Introduction
139(2)
References
141(2)
6 Self-correcting Connectionist Parsing
143(26)
John E. Rager
Introduction: Constrained chaos
143(5)
Agreement
148(6)
Counting
154(3)
Constituent motion
157(6)
Missing constituents
163(2)
Conclusions
165(1)
Acknowledgements
166(1)
References
167(2)
7 A Net-linguistic "Earley" Parser
169(40)
H. Schnelle
R. Doust
Introduction
169(1)
The basic characteristics of the parser
170(8)
The representation of parse-information
178(5)
The Earley parse-list algorithm
183(4)
Our approach
187(15)
References
202(1)
Appendix
203(6)
PART III REPRESENTATIONAL ADEQUACY
Introduction
209(2)
References
211(2)
8 The Demons and the Beast---Modular and Nodular Kinds of Knowledge
213(40)
Thomas G. Bever
Introduction and summary
213(1)
Structure and habits---The knowledge and the power
214(6)
A model that learns some morphology
220(8)
Evidence for nodes unseen---some models that learn to read aloud
228(12)
The study of statistically available information
240(9)
Conclusion---Behavioural strategies and mental structures
249(1)
Acknowledgements
250(1)
References
250(3)
9 Representational Adequacy and the Case for a Hybrid Connectionist/Marker-parsing Model
253(20)
George Berg
Introduction
253(1)
Representational adequacy
254(3)
Autonomous semantic networks
257(3)
ASNs and representational adequacy
260(7)
Discussion
267(3)
Conclusion
270(1)
Acknowledgements
271(1)
References
271(2)
10 A Step Toward Sub-symbolic Language Models without Linguistic Representations
273(44)
George Dorffner
Introduction
273(2)
Basic observations about language
275(9)
An implementation
284(2)
Categorisation and concept formation
286(11)
Implementing symbols
297(7)
The output component
304(1)
A more complex example
304(5)
Future directions
309(1)
Summary and conclusion
310(1)
Acknowledgements
311(1)
References
311(2)
Appendix
313(4)
PART IV COMPUTATIONAL PSYCHOLINGUISTICS Introduction
317(144)
References
319(2)
11 Connectionist Models of Speech Perception
321(30)
Dominic W. Massaro
Introduction
321(2)
Phonological constraints in speech perception
323(5)
Interactive activation models
328(10)
Auditory/visual speech perception
338(5)
Feedforward connectionist models
343(5)
Discussion
348(1)
Acknowledgements
348(1)
References
348(3)
12 Connectionism: A New Breed of Bottom-up Model?
351(22)
Dennis Norris
Introduction
351(1)
Interactive activation models
352(3)
A simple network for word and letter recognition
355(3)
Elman and McClelland's study
358(2)
A dynamic net model of word recognition
360(7)
Conclusions
367(3)
References
370(3)
13 Models of Form-related Priming in Comprehension and Production
373(36)
Padraig G. O'Seaghdha
Gary S. Dell
Robert R. Peterson
Cornell Juliano
Introduction
373(1)
Receptive priming
374(3)
The models
377(27)
Conclusions
404(1)
Acknowledgements
405(1)
References
406(3)
14 Reading with Attentional Impairments: A Brain-damaged Model of Neglect and Attentional Dyslexias
409(52)
Michael C. Mozer
Marlene Behrmann
Introduction
409(2)
MORSEL
411(10)
Simulations of neglect dyslexia
421(22)
Attentional dyslexia
443(3)
Discussion
446(3)
Acknowledgements
449(1)
References
449(3)
Appendix 1 PO net dynamics
452(2)
Appendix 2 AM dynamics
454(2)
Appendix 3 Details of AM simulations
456(1)
Appendix 4 Details of BLIRNET and PO net simulations
457(4)
Author Index 461(8)
Subject Index 469
R G Reilly, Noel Sharkey