Muutke küpsiste eelistusi

E-raamat: Cognitive Approach to Natural Language Processing

(University of Technology, Poland), (Professor, Paul Sabatier University, Toulouse, France), (Staffordshire University, UK)
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 31-May-2017
  • Kirjastus: ISTE Press Ltd - Elsevier Inc
  • Keel: eng
  • ISBN-13: 9780081023433
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 107,84 €*
  • * 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.
Cognitive Approach to Natural Language ProcessingSuurem pilt
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 31-May-2017
  • Kirjastus: ISTE Press Ltd - Elsevier Inc
  • Keel: eng
  • ISBN-13: 9780081023433
Teised raamatud teemal:

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. 

NLP crosses many disciplines namely Computational Linguistics, Artificial Intelligence, Cognitive Linguistics, Computer Science and Cognitive Science. In this interdisciplinary approach to language processing we provide a forum to foster interactions among researchers and practitioners in Natural Language Processing (NLP) by taking a Cognitive Science perspective and learning from recent advances in Cognitive Neuroscience, Cognitive Linguistics and Neurolinguistics.
  • As NLP crosses many disciplines it is difficult sometimes to understand the contributions and the challenges of each discipline
  • The aim of this book is to discuss the problems and issues that researchers face and provide an opportunity for developers of NLP systems to learn from cognitive scientists as well as cognitive linguistics and neurolinguistics, and vice versa
  • This book will provide a valuable opportunity to link the study of natural language processing to the understanding of the cognitive processes of the brain

Arvustused

"All in all, for a computer scientist specializing in areas like computational linguistics, natural language processing, robotics, chatbots, navigation systems, speech recognition, and perhaps processing of sign languages, from an interdisciplinary point of view, this is an excellent starting point." --Computer Reviews

Muu info

Takes a cognitive science perspective and learning from recent advances in cognitive neuroscience, cognitive linguistics and neurolinguistics
Preface xi
Chapter 1 Delayed Interpretation, Shallow Processing and Constructions: the Basis of the "Interpret Whenever Possible" Principle
1(20)
Philippe Blache
1.1 Introduction
1(2)
1.2 Delayed processing
3(2)
1.3 Working memory
5(3)
1.4 How to recognize chunks: the segmentation operations
8(2)
1.5 The delaying architecture
10(6)
1.5.1 Segment-and-store
11(1)
1.5.2 Aggregating by cohesion
12(4)
1.6 Conclusion
16(1)
1.7 Bibliography
17(4)
Chapter 2 Can the Human Association Norm Evaluate Machine-Made Association Lists?
21(20)
Michal Korzycki
Izabela Gatkowska
Wiestaw Lubaszewskl
2.1 Introduction
21(2)
2.2 Human semantic associations
23(6)
2.2.1 Word association test
23(1)
2.2.2 The author's experiment
24(1)
2.2.3 Human association topology
25(1)
2.2.4 Human associations are comparable
26(3)
2.3 Algorithm efficiency comparison
29(8)
2.3.1 The corpora
29(1)
2.3.2 LSA-sourced association lists
29(2)
2.3.3 LDA-sourced lists
31(1)
2.3.4 Association ratio-based lists
31(1)
2.3.5 List comparison
32(5)
2.4 Conclusion
37(1)
2.5 Bibliography
38(3)
Chapter 3 How a Word of a Text Selects the Related Words in a Human Association Network
41(22)
Wiestaw Lubaszewski
Izabela Gatkowska
Maciej Godny
3.1 Introduction
41(3)
3.2 The network
44(2)
3.3 The network extraction driven by a text-based stimulus
46(4)
3.3.1 Sub-graph extraction algorithm
46(2)
3.3.2 The control procedure
48(1)
3.3.3 The shortest path extraction
48(2)
3.3.4 A Corpus-Based Sub-Graph
50(1)
3.4 Tests of the network extracting procedure
50(8)
3.4.1 The corpus to perform tests
50(1)
3.4.2 Evaluation of the extracted sub-graph
51(1)
3.4.3 Directed and undirected sub-graph extraction: the comparison
52(1)
3.4.4 Results per stimulus
53(5)
3.5 A Brief Discussion of the Results and the Related Work
58(2)
3.6 Bibliography
60(3)
Chapter 4 The Reverse Association Task
63(28)
Reinhard Rapp
4.1 Introduction
63(4)
4.2 Computing forward associations
67(4)
4.2.1 Procedure
67(2)
4.2.2 Results and evaluation
69(2)
4.3 Computing reverse associations
71(7)
4.3.1 Problem
71(1)
4.3.2 Procedure
71(5)
4.3.3 Results and evaluation
76(2)
4.4 Human performance
78(4)
4.4.1 Dataset
78(2)
4.4.2 Test procedure
80(1)
4.4.3 Evaluation
81(1)
4.5 Performance by machine
82(2)
4.6 Discussion, conclusions and outlook
84(3)
4.6.1 Reverse associations by a human
84(1)
4.6.2 Reverse associations by a machine
85(2)
4.7 Acknowledgments
87(1)
4.8 Bibliography
88(3)
Chapter 5 Hidden Structure and Function in the Lexicon
91(18)
Philippe Vincent-Lamarre
Melanie Lord
Alexandre Blondin-Masse
Odile Marcotte
Marcos Lopes
Stevan Harnad
5.1 Introduction
91(1)
5.2 Methods
92(5)
5.2.1 Dictionary graphs
92(4)
5.2.2 Psycholinguistic variables
96(1)
5.2.3 Data analysis
96(1)
5.3 Psycholinguistic properties of Kernel, Satellites, Core, MinSets and the rest of each dictionary
97(4)
5.4 Discussion
101(3)
5.4.1 Limitations
104(1)
5.5 Future work
104(2)
5.6 Bibliography
106(3)
Chapter 6 Transductive Learning Games for Word Sense Disambiguation
109(20)
Rocco Tripodi
Marcello Pelillo
6.1 Introduction
109(2)
6.2 Graph-based word sense disambiguation
111(2)
6.3 Our approach to semi-supervised learning
113(3)
6.3.1 Graph-based semi-supervised learning
113(1)
6.3.2 Game theory and game dynamics
114(2)
6.4 Word sense disambiguation games
116(4)
6.4.1 Graph construction
116(1)
6.4.2 Strategy space
117(1)
6.4.3 The payoff matrix
118(1)
6.4.4 System dynamics
119(1)
6.5 Evaluation
120(4)
6.5.1 Experimental setting
120(1)
6.5.2 Evaluation results
121(3)
6.5.3 Comparison with state-of-the-art algorithms
124(1)
6.6 Conclusion
124(1)
6.7 Bibliography
125(4)
Chapter 7 Use Your Mind and Learn to Write: The Problem of Producing Coherent Text
129(30)
Michael Zock
Debela Tesfaye Gemechu
7.1 The problem
129(2)
7.2 Suboptimal texts and some of the reasons
131(4)
7.2.1 Lack of coherence or cohesion
132(1)
7.2.2 Faulty reference
133(1)
7.2.3 Unmotivated topic shift
134(1)
7.3 How to deal with the complexity of the task?
135(1)
7.4 Related work
136(2)
7.5 Assumptions concerning the building of a tool assisting the writing process
138(3)
7.6 Methodology
141(10)
7.6.1 Identification of the syntactic structure
143(1)
7.6.2 Identification of the semantic seed words
144(1)
7.6.3 Word alignment
145(1)
7.6.4 Determination of the similarity values of the aligned words
146(4)
7.6.5 Determination of the similarity between sentences
150(1)
7.6.6 Sentence clustering based on their similarity values
151(1)
7.7 Experiment and evaluation
151(3)
7.8 Outlook and conclusion
154(1)
7.9 Bibliography
155(4)
Chapter 8 Stylistic Features Based on Sequential Rule Mining for Authorship Attribution
159(18)
Mohamed Amine Boukhaled
Jean-Gabriel Ganascia
8.1 Introduction and motivation
159(3)
8.2 The authorship attribution process
162(1)
8.3 Stylistic features for authorship attribution
163(2)
8.4 Sequential data mining for stylistic analysis
165(1)
8.5 Experimental setup
166(3)
8.5.1 Dataset
166(1)
8.5.2 Classification scheme
167(2)
8.6 Results and discussion
169(4)
8.7 Conclusion
173(1)
8.8 Bibliography
173(4)
Chapter 9 A Parallel, Cognition-oriented Fundamental Frequency Estimation Algorithm
177(20)
Ulrike Glavitsch
9.1 Introduction
177(3)
9.2 Segmentation of the speech signal
180(4)
9.2.1 Speech and pause segments
180(2)
9.2.2 Voiced and unvoiced regions
182(1)
9.2.3 Stable and unstable intervals
183(1)
9.3 F0 estimation for stable intervals
184(2)
9.4 F0 propagation
186(5)
9.4.1 Control flow
187(2)
9.4.2 Peak propagation
189(2)
9.5 Unstable voiced regions
191(1)
9.6 Parallelization
191(1)
9.7 Experiments and results
192(2)
9.8 Conclusions
194(1)
9.9 Acknowledgments
195(1)
9.10 Bibliography
195(2)
Chapter 10 Benchmarking n-grams, Topic Models and Recurrent Neural Networks by Cloze Completions, EEGs and Eye Movements
197(20)
Markus J. Hofmann
Chris Biemann
Steffen Remus
10.1 Introduction
198(1)
10.2 Related work
199(1)
10.3 Methodology
200(3)
10.3.1 Human performance measures
200(1)
10.3.2 Three flavors of language models
201(2)
10.4 Experiment setup
203(1)
10.5 Results
204(6)
10.5.1 Predictability results
204(2)
10.5.2 N400 amplitude results
206(2)
10.5.3 Single-fixation duration (SFD) results
208(2)
10.6 Discussion and conclusion
210(2)
10.7 Acknowledgments
212(1)
10.8 Bibliography
212(5)
List of Authors 217(2)
Index 219
Bernadette Sharp is Professor of Applied Artificial Intelligence (AI) at Staffordshire University, UK. Her research interests include AI, natural language processing, and text mining. She has been Chair and Editor of the International Workshop for Natural Language Processing and Cognitive Science since 2004. Florence Sèdes is a Professor of Computer Science at Paul Sabatier University, Toulouse, France. Her research focuses on data science, and she has published many books and articles and advised more than 30 PhDs. She leads various international, European and national projects on personal (meta)data privacy and management with applications to deep/machine learning for alert, spam and rumor detection, social emotion and interaction Wiesaw Lubaszewski is Professor at the Department of Computational Linguistics of the Jagiellonian University and Professor at the Computer Science Department of AGH, University of Technology, in Kraków, Poland. His research interests include natural language dictionaries, text understanding, knowledge representation, and information extraction.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97800810234336e.html
Märksõnad: