Natural language processing and information retrieval /
Siddiqui, Tanveer.
Natural language processing and information retrieval / Tanveer Siddiqui, U.S. Tiwary. - 1st ed - New Delhi ; New York : Oxford Univ Press, c2008. - ix, 406 p. : ill. ; 25 cm.
Includes bibliographical references and index.
1. Introduction
Chapter Overview 1
1.1 What is Natural Language Processing (NLP) 1
1.2 Origins of NLP 2
1.3 Language and Knowledge 3
1.4 The Challenges of NLP 6
1.5 Language and Grammar 8
1.6 Processing Indian Languages 12
1.7 NLP Applications 13
1.8 Some Successful Early NLP Systems 15
1.9 Information Retrieval 16
2. Language Modelling 21
Chapter Overview 21
2.1 Introduction 21
2.2 Various Grammar-based Language Models 22
2.3 Statistical Language Model 45
3. Word Level Analysis 53
Chapter Overview 53
3.1 Introduction 53
3.2 Regular Expressions 54
3.3 Finite-State Automata 59
3.4 Morphological Parsing 63
3.5 Spelling Error Detection and Correction 71
3.6 Words and Word Classes 76
3.7 Part-of-Speech Tagging 77
4. Syntactic Analysis 92
Chapter Overview 92
4.1 Introduction 92
4.2 Context-Free Grammar 93
4.3 Constituency 95
4.4 Parsing 104
4.5 Probabilistic Parsing 119
4.6 Indian Languages 125
5. Semantic Analysis 132
Chapter Overview 132
5.1 Introduction 132
5.2 Meaning Representation 134
5.3 Lexical Semantics 145
5.4 Ambiguity 151
5.5 Word Sense Disambiguation 156
6. Discourse Processing 179
Chapter Overview 179
6.1 Introduction 179
6.2 Cohesion 181
6.3 Reference Resolution 185
6.4 Discourse Coherence and Structure 196
7. Natural Language Generation 209
Chapter Overview 209
7.1 Introduction 209
7.2 Architectures of NLG Systems 210
7.3 Generation Tasks apd Representations 213
7.4 Applications of NLI 223
8. Machine Translation 228
Chapter Overview 228
8.1 Introduction 228
8.2 Problems in Machine Translation 229
8.3 Characteristics of Indian Languages 230
8.4 Machine Translation Approaches 231
8.5 Direct Machine Translation 232
8.6 Rule-based Machine Translation 236
8.7 Corpus-based Machine Translation 241
8.8 Semantic or Knowledge-based MT systems 249
8.9 Translation involving Indian Languages 250
9. Information Retrieval-1 255
Chapter Overview 255
9.1 Introduction 255
9.2 Design Features of Information Retrieval systems 256
9.3 Information Retrieval Models 261
9.4 Classical Information Retrieval Models 262
9.5 Non-classical models of IR 274
9.6 Alternative Models of IR 275
9.7 Evaluation of the IR System 283
10. Information Retrieval-2 300
Chapter Overview 300
10.1 Introduction 300
10.2 Natural Language Processing in IR 301
10.3 Relation Matching 304
10.4 Knowledge-based Approaches 305
10.5 Conceptual Graphs in IR 307
10.6 Cross-lingual Information Retrieval 328
11. Other Applications 336
Chapter Overview 336
11.1 Introduction 336
11.2 Information Extraction 337
11.3 Automatic Text Summarization 343
11.4 Question-Answering System 358
12. Lexical Resources 371
Chapter Overview 371
12.1 Introduction 371
12.2 WordNet 372
12.3 FrameNet 376
12.4 Stemmers 378
12.5 Part-of-Speech Tagger 379
12.6 Research Corpora 383
12.7 Journals and Conferences in the Area 385
9780195692327 0195692322
2008300442
Natural language processing (Computer science)
Computational linguistics.
Information retrieval.
QA76.9.N38 / S52 2008
006.35 / S.T.N 2008
Natural language processing and information retrieval / Tanveer Siddiqui, U.S. Tiwary. - 1st ed - New Delhi ; New York : Oxford Univ Press, c2008. - ix, 406 p. : ill. ; 25 cm.
Includes bibliographical references and index.
1. Introduction
Chapter Overview 1
1.1 What is Natural Language Processing (NLP) 1
1.2 Origins of NLP 2
1.3 Language and Knowledge 3
1.4 The Challenges of NLP 6
1.5 Language and Grammar 8
1.6 Processing Indian Languages 12
1.7 NLP Applications 13
1.8 Some Successful Early NLP Systems 15
1.9 Information Retrieval 16
2. Language Modelling 21
Chapter Overview 21
2.1 Introduction 21
2.2 Various Grammar-based Language Models 22
2.3 Statistical Language Model 45
3. Word Level Analysis 53
Chapter Overview 53
3.1 Introduction 53
3.2 Regular Expressions 54
3.3 Finite-State Automata 59
3.4 Morphological Parsing 63
3.5 Spelling Error Detection and Correction 71
3.6 Words and Word Classes 76
3.7 Part-of-Speech Tagging 77
4. Syntactic Analysis 92
Chapter Overview 92
4.1 Introduction 92
4.2 Context-Free Grammar 93
4.3 Constituency 95
4.4 Parsing 104
4.5 Probabilistic Parsing 119
4.6 Indian Languages 125
5. Semantic Analysis 132
Chapter Overview 132
5.1 Introduction 132
5.2 Meaning Representation 134
5.3 Lexical Semantics 145
5.4 Ambiguity 151
5.5 Word Sense Disambiguation 156
6. Discourse Processing 179
Chapter Overview 179
6.1 Introduction 179
6.2 Cohesion 181
6.3 Reference Resolution 185
6.4 Discourse Coherence and Structure 196
7. Natural Language Generation 209
Chapter Overview 209
7.1 Introduction 209
7.2 Architectures of NLG Systems 210
7.3 Generation Tasks apd Representations 213
7.4 Applications of NLI 223
8. Machine Translation 228
Chapter Overview 228
8.1 Introduction 228
8.2 Problems in Machine Translation 229
8.3 Characteristics of Indian Languages 230
8.4 Machine Translation Approaches 231
8.5 Direct Machine Translation 232
8.6 Rule-based Machine Translation 236
8.7 Corpus-based Machine Translation 241
8.8 Semantic or Knowledge-based MT systems 249
8.9 Translation involving Indian Languages 250
9. Information Retrieval-1 255
Chapter Overview 255
9.1 Introduction 255
9.2 Design Features of Information Retrieval systems 256
9.3 Information Retrieval Models 261
9.4 Classical Information Retrieval Models 262
9.5 Non-classical models of IR 274
9.6 Alternative Models of IR 275
9.7 Evaluation of the IR System 283
10. Information Retrieval-2 300
Chapter Overview 300
10.1 Introduction 300
10.2 Natural Language Processing in IR 301
10.3 Relation Matching 304
10.4 Knowledge-based Approaches 305
10.5 Conceptual Graphs in IR 307
10.6 Cross-lingual Information Retrieval 328
11. Other Applications 336
Chapter Overview 336
11.1 Introduction 336
11.2 Information Extraction 337
11.3 Automatic Text Summarization 343
11.4 Question-Answering System 358
12. Lexical Resources 371
Chapter Overview 371
12.1 Introduction 371
12.2 WordNet 372
12.3 FrameNet 376
12.4 Stemmers 378
12.5 Part-of-Speech Tagger 379
12.6 Research Corpora 383
12.7 Journals and Conferences in the Area 385
9780195692327 0195692322
2008300442
Natural language processing (Computer science)
Computational linguistics.
Information retrieval.
QA76.9.N38 / S52 2008
006.35 / S.T.N 2008