Muutke küpsiste eelistusi

Computational Techniques for Text Summarization based on Cognitive Intelligence [Kõva köide]

,
  • Formaat: Hardback, 216 pages, kõrgus x laius: 229x152 mm, kaal: 420 g, 20 Tables, black and white; 5 Line drawings, black and white; 48 Halftones, black and white; 53 Illustrations, black and white
  • Ilmumisaeg: 17-Mar-2023
  • Kirjastus: CRC Press
  • ISBN-10: 1032392827
  • ISBN-13: 9781032392820
Teised raamatud teemal:
Computational Techniques for Text Summarization based on Cognitive IntelligenceSuurem pilt
  • Formaat: Hardback, 216 pages, kõrgus x laius: 229x152 mm, kaal: 420 g, 20 Tables, black and white; 5 Line drawings, black and white; 48 Halftones, black and white; 53 Illustrations, black and white
  • Ilmumisaeg: 17-Mar-2023
  • Kirjastus: CRC Press
  • ISBN-10: 1032392827
  • ISBN-13: 9781032392820
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781032392820.html
Märksõnad:

The book is concerned with contemporary methodologies used for automatic text summarization. It proposes interesting approaches to solve well-known problems on text-summarization using computational intelligence (CI) techniques including cognitive approaches.



The book is concerned with contemporary methodologies used for automatic text summarization. It proposes interesting approaches to solve well-known problems on text summarization using computational intelligence (CI) techniques including cognitive approaches. A better understanding of the cognitive basis of the summarization task is still an open research issue; an extent of its use in text summarization is highlighted for further exploration. With the ever-growing text, people in research have little time to spare for extensive reading, where summarized information helps for a better understanding of the context at a shorter time.

This book helps students and researchers to automatically summarize the text documents in an efficient and effective way. The computational approaches and the research techniques presented guides to achieve text summarization at ease. The summarized text generated supports readers to learn the context or the domain at a quicker pace. The book is presented with reasonable amount of illustrations and examples convenient for the readers to understand and implement for their use. It is not to make readers understand what text summarization is, but for people to perform text summarization using various approaches. This also describes measures that can help to evaluate, determine, and explore the best possibilities for text summarization to analyse and use for any specific purpose. The illustration is based on social media and healthcare domain, which shows the possibilities to work with any domain for summarization. The new approach for text summarization based on cognitive intelligence is presented for further exploration in the field.

Preface ix
About This Book xi
Chapter 1 Concepts of Text Summarization
1(22)
1.1 Introduction
1(1)
1.2 Need for Text Summarization
1(1)
1.3 Approaches to Text Summarization
2(1)
1.3.1 Extractive Summarization
2(1)
1.3.2 Abstractive Summarization
2(1)
1.4 Text Modeling for Extractive Summarization
3(8)
1.4.1 Bag-of-Words Model
3(2)
1.4.2 Vector Space Model
5(4)
1.4.3 Topic Representation Schemes
9(2)
1.4.4 Real-Valued Model
11(1)
1.5 Preprocessing for Extractive Summarization
11(4)
1.6 Emerging Techniques for Summarization
15(1)
1.7 Scope of the Book
16(2)
References
18(1)
Sample Code
19(4)
Sample Screenshots
22(1)
Chapter 2 Large-Scale Summarization Using Machine Learning Approach
23(24)
2.1 Scaling to Summarize Large Text
23(1)
2.2 Machine Learning Approaches
23(21)
2.2.1 Different Approaches for Modeling Text Summarization Problem
24(1)
2.2.2 Classification as Text Summarization
24(1)
2.2.2.1 Data Representation
24(3)
2.2.2.2 Text Feature Extraction
27(2)
2.2.2.3 Classification Techniques
29(3)
2.2.3 Clustering as Text Summarization
32(4)
2.2.4 Deep Learning Approach for Text Summarization
36(8)
References
44(1)
Sample Code
45(2)
Chapter 3 Sentiment Analysis Approach to Text Summarization
47(16)
3.1 Introduction
47(1)
3.2 Sentiment Analysis: Overview
47(7)
3.2.1 Sentiment Extraction and Summarization
47(1)
3.2.1.1 Sentiment Extraction from Text
48(1)
3.2.1.2 Classification
48(1)
3.2.1.3 Score Computation
48(1)
3.2.1.4 Summary Generation
49(1)
3.2.2 Sentiment Summarization: An Illustration
49(1)
Summarized Output
50(1)
3.2.3 Methodologies for Sentiment Summarization
51(3)
3.3 Implications of Sentiments in Text Summarization
54(2)
Cognition-Based Sentiment Analysis and Summarization
55(1)
3.4 Summary
56(1)
Practical Examples
56(2)
Example 1
56(1)
Example 2
57(1)
Sample Code (Run Using GraphLab)
58(1)
Example 3
58(1)
References
59(1)
Sample Code
60(3)
Chapter 4 Text Summarization Using Parallel Processing Approach
63(34)
4.1 Introduction
63(1)
Parallelizing Computational Tasks
63(1)
Parallelizing for Distributed Data
63(1)
4.2 Parallel Processing Approaches
63(4)
4.2.1 Parallel Algorithms for Text Summarization
64(1)
4.2.2 Parallel Bisection k-Means Method
64(3)
4.3 Parallel Data Processing Algorithms for Large-Scale Summarization
67(8)
4.3.1 Designing MapReduce Algorithm for Text Summarization
67(1)
4.3.2 Key Concepts in Mapper
68(1)
4.3.3 Key Concepts in Reducer
69(2)
4.3.4 Summary Generation
71(1)
An Illustrative Example for MapReduce
71(1)
Good Time: Movie Review
71(4)
4.4 Other MR-Based Methods
75(6)
4.5 Summary
81(1)
4.6 Examples
81(6)
K-Means Clustering Using MapReduce
81(1)
Parallel LDA Example (Using Gensim Package)
81(2)
Sample Code: (Using Gensim Package)
83(1)
Example: Creating an Inverted Index
83(2)
Example: Relational Algebra (Table JOIN)
85(2)
References
87(1)
Sample Code
88(9)
Chapter 5 Optimization Approaches for Text Summarization
97(22)
5.1 Introduction
97(1)
5.2 Optimization for Summarization
97(1)
5.2.1 Modeling Text Summarization as Optimization Problem
98(1)
5.2.2 Various Approaches for Optimization
98(1)
5.3 Formulation of Various Approaches
98(13)
5.3.1 Sentence Ranking Approach
98(2)
5.3.1.1 Stages and Illustration
100(1)
5.3.2 Evolutionary Approaches
101(1)
5.3.2.1 Stages
101(1)
5.3.2.2 Demonstration
102(2)
5.3.3 MapReduce-Based Approach
104(1)
5.3.3.1 In-Node Optimization Illustration
105(1)
5.3.4 Multi-objective-Based Approach
106(5)
Summary
111(1)
Exercises
112(4)
References
116(1)
Sample Code
117(2)
Chapter 6 Performance Evaluation of Large-Scale Summarization Systems
119(14)
6.1 Evaluation of Summaries
119(3)
6.1.1 CNNDataset
120(1)
6.1.2 Daily Mail Dataset
120(1)
6.1.3 Description
121(1)
6.2 Methodologies
122(1)
6.2.1 Intrinsic Methods
122(1)
6.2.2 Extrinsic Methods
122(1)
6.3 Intrinsic Methods
122(5)
6.3.1 Text Quality Measures
122(1)
6.3.1.1 Grammaticality
122(1)
6.3.1.2 Non-redundancy
122(1)
6.3.1.3 Reverential Clarity
123(1)
6.3.1.4 Structure and Coherence
123(1)
6.3.2 Co-selection-Based Methods
123(1)
6.3.2.1 Precision, Recall, and F-score
123(1)
6.3.2.2 Relative Utility
124(1)
6.3.3 Content-Based Methods
124(1)
6.3.3.1 Content-Based Measures
124(1)
6.3.3.2 Cosine Similarity
125(1)
6.3.3.3 Unit Overlap
125(1)
6.3.3.4 Longest Common Subsequence
125(1)
6.3.3.5 N-Gram Co-occurrence Statistics: ROUGE
125(1)
6.3.3.6 Pyramids
126(1)
6.3.3.7 LSA-Based Measure
126(1)
6.3.3.8 Main Topic Similarity
126(1)
6.3.3.9 Term Significance Similarity
126(1)
6.4 Extrinsic Methods
127(5)
6.4.1 Document Categorization
127(1)
6.4.1.1 Information Retrieval
127(1)
6.4.1.2 Question Answering
128(1)
6.4.2 Summary
128(1)
6.4.3 Examples
128(4)
Bibliography
132(1)
Chapter 7 Applications and Future Directions
133(10)
7.1 Possible Directions in Modeling Text Summarization
133(1)
7.2 Scope of Summarization Systems in Different Applications
133(1)
7.3 Healthcare Domain
134(2)
Future Directions for Medical Document Summarization
135(1)
7.4 Social Media
136(3)
Challenges in Social Media Text Summarization
138(1)
Domain Knowledge and Transfer Learning
138(1)
Online Learning
138(1)
Information Credibility
138(1)
Applications of Deep Learning
138(1)
Implicit and Explicit Information for Actionable Insights
139(1)
7.5 Research Directions for Text Summarization
139(2)
7.6 Further Scope of Research on Large-Scale Summarization
141(1)
Conclusion
141(1)
References
141(2)
Appendix A Python Projects and Useful Links on Text Summarization 143(56)
Appendix B Solutions to Selected Exercises 199(12)
Index 211
V. Priya is presently working as an assistant professor in, the department of computer science and engineering, Dr. N. G. P. Institute of Technology, Coimbatore, India. Her areas of research include text summarization using map-reduce and optimization along with an application. She has taught courses such as big data, data warehousing, and mining, operating systems, data management, and analytics at undergraduate and graduate levels. She has published research papers in journals of national and international repute.

K. Umamaheswari is currently working as a professor and head of, the department of information technology, PSG College of Technology, India. She has more than twenty-five years of teaching experience and has published more than a hundred papers in journals and conferences of national and international repute. Her research interests include data mining, cognitive networks, text mining, and information retrieval. She is the senior editor for the National Journal of Technology and reviewers for many national and international journals.