상세정보

Information Retrieval: Algorithms and Heuristics is a comprehensive introduction to the study of information retrieval covering both effectiveness and run-time performance. The focus of the presentation is on algorithms and heuristics used to find documents relevant to the user request and to find them fast. Through multiple examples, the most commonly used algorithms and heuristics needed are tackled. To facilitate understanding and applications, introductions to and discussions of computational linguistics, natural language processing, probability theory and library and computer science are provided. While this text focuses on algorithms and not on commercial product per se, the basic strategies used by many commercial products are described. Techniques that can be used to find information on the Web, as well as in other large information collections, are included.
This volume is an invaluable resource for researchers, practitioners, and students working in information retrieval and databases. For instructors, a set of Powerpoint slides, including speaker notes, are available online from the authors.

Information Retrieval: Algorithms and Heuristics is a comprehensive introduction to the study of information retrieval covering both effectiveness and run-time performance. The focus of the presentation is on algorithms and heuristics used to find documents relevant to the user request and to find them fast. Through multiple examples, the most commonly used algorithms and heuristics needed are tackled. To facilitate understanding and applications, introductions to and discussions of computational linguistics, natural language processing, probability theory and library and computer science are provided. While this text focuses on algorithms and not on commercial product per se, the basic strategies used by many commercial products are described. Techniques that can be used to find information on the Web, as well as in other large information collections, are included.
This volume is an invaluable resource for researchers, practitioners, and students working in information retrieval and databases. For instructors, a set of Powerpoint slides, including speaker notes, are available online from the authors.

정보제공 :

CONTENTS

List of Figures = ⅶ

Preface = ⅸ

Acknowledgments = xv

1. INTRODUCTION = 1

2. RETRIEVAL STRATEGIES = 1

 2.1 Vector Space Model = 13

 2.2 Probabilistic Retrieval strategies = 22

 2.3 Inference Networks = 48

 2.4 Extended Boolean Retrieval = 58

 2.5 Latent Semantic Indexing = 60

 2.6 Neural Networks = 64

 2.7 Genetic Algorithms = 70

 2.8 Fuzzy Set Retrieval = 74

 2.9 Summary = 80

 2.10 Exercises = 81

3. RETRIEVAL UTILITIES = 83

 3.1 Relevance Feedback = 84

 3.2 Clustering = 94

 3.3 Passage-based Retrieval = 100

 3.4 N-grams = 102

 3.5 Regression analysis = 106

 3.6 Thesauri = 108

 3.7 Semantic Networks = 118

 3.8 Parsing = 125

 3.9 Summary = 131

 3.10 Exercises = 131

4. EFFICIENCY ISSUES PERTAINING TO SEQUENTIAL IR SYSTEMS = 133

 4.1 Inverted Index = 134

 4.2 Query Processing = 142

 4.3 Signature Files = 146

 4.4 Summary = 149

 4.5 Exercises = 150

5. INTEGRATING STRUCTURED DATA AND TEXT = 153

 5.1 Review of the Relational Model = 157

 5.2 A historical Progression = 163

 5.3 Information Retrieval functionality Using the Relational Model = 168

 5.4 Boolean Retrieval = 176

 5.5 Proximity Searches = 179

 5.6 Computing Relevance Using Unchanged SQL = 181

 5.7 Relevance Feedback in the Relational Model = 183

 5.8 Summary = 184

 5.9 Exercises = 184

6. PARALLEL INFORMATION RETRIEVAL SYSTEMS = 185

 6.1 Parallel Text Scanning = 186

 6.2 Parallel Indexing = 191

 6.3 Parrllel Implementation of Clustering and Classification = 198

 6.4 Summary = 198

 6.5 Exercises = 199

7. DISTRIBUTED INFORMATION RETRIEVAL = 201

 7.1 A Theoretical Model of Distributed IR = 202

 7.2 Replication in Distributed IR Systems = 206

 7.3 Implementation Issues of a Distributed IR System = 209

 7.4 Improving Performance of Web-based IR Systems = 212

 7.5 Web Search Engines = 214

 7.6 Summary = 217

 7.7 Exercises = 219

8. THE TEXT RETRIEVAL CONFERENCE (TREC) = 221

9. FUTURE DIRECTIONS = 227

References = 231

Index = 253