Text Mining for Biology And Biomedicine

Contents......Page 6
1.1 Text Mining: Aims, Challenges, and Solutions 1......Page 14
1.2 Outline of the Book 7......Page 20
References......Page 24
2.1 Introduction 13......Page 26
2.2.1 Tokenization 16......Page 29
2.2.2 Morphological Analysis 18......Page 31
2.2.3 Linguistic Lexicons 19......Page 32
2.3 The Syntactic Level of Natural Language Processing 21......Page 34
2.3.1 Part-of-Speech Tagging 22......Page 35
2.3.2 Chunking 23......Page 36
2.4.1 Lexical Semantic Interpretation 25......Page 38
2.4.2 Semantic Interpretation of Utterances 27......Page 40
2.5.1 General Architecture 31......Page 44
2.5.2 Two Concrete System Architectures 35......Page 48
2.6 Conclusions and Outlook 36......Page 49
References......Page 51
3.1 Introduction 43......Page 56
3.2.1 Entity Recognition 45......Page 58
3.2.2 Relation Extraction 46......Page 59
3.3.1 WordNet 48......Page 61
3.3.3 Other Specialized Resources 49......Page 62
3.4.1 Gene Ontology 50......Page 63
3.4.2 Medical Subject Headings 53......Page 66
3.4.3 UMLS Metathesaurus 54......Page 67
3.5 Ontological Resources 55......Page 68
3.5.2 UMLS Semantic Network 56......Page 69
3.6 Issues Related to Entity Recognition 58......Page 71
3.6.1 Limited Coverage 59......Page 72
3.7.1 Terminological Versus Ontological Relations 60......Page 73
3.8 Conclusion 61......Page 74
References......Page 75
4.1.1 Principles of Terminology 67......Page 80
4.2 Terminological Resources in Biomedicine 70......Page 83
4.3 Automatic Terminology Management 72......Page 85
4.4 Automatic Term Recognition 73......Page 86
4.4.1 Dictionary-Based Approaches 74......Page 87
4.4.3 Machine Learning Approaches 75......Page 88
4.4.4 Statistical Approaches 76......Page 89
4.4.5 Hybrid Approaches 77......Page 90
4.5.1 Term Variations 78......Page 91
4.5.2 Term Ambiguity 82......Page 95
4.6 Automatic Term Structuring 83......Page 96
4.7 Examples of Automatic Term Management Systems 86......Page 99
4.8 Conclusion 90......Page 103
References......Page 105
5.1 Introduction 99......Page 112
5.2 Identifying Abbreviations 103......Page 116
5.2.1 Heuristics 104......Page 117
5.2.2 Alignment 105......Page 118
5.2.4 Stanford Biomedical Abbreviation Method 106......Page 119
5.2.5 Evaluating Abbreviation Identification Methods 109......Page 122
5.3 Normalizing Abbreviations 112......Page 125
5.4 Defining Abbreviations in Text 115......Page 128
5.5 Abbreviation Databases 116......Page 129
References......Page 130
6.1 Introduction 121......Page 134
6.2 Biomedical Named Entities 124......Page 137
6.3.1 Ambiguous Names 126......Page 139
6.3.3 Variations 127......Page 140
6.3.4 Names of Newly Discovered Genes and Proteins 128......Page 141
6.4 Approaches to Gene and Protein Name Recognition 129......Page 142
6.4.1 Dictionary-Based Approaches 130......Page 143
6.4.2 Rule-Based Approaches 131......Page 144
6.4.3 Machine Learning Approaches 132......Page 145
6.4.4 Hybrid Approaches 134......Page 147
6.4.5 Classification and Grounding of Biomedical  Named Entities 135......Page 148
6.5 Discussion 136......Page 149
References......Page 151
7.1 Information Extraction: The Task 143......Page 156
7.1.1 Information Extraction and Information Retrieval 144......Page 157
7.1.2 Information Extraction and Natural Language  Processing 145......Page 158
7.2.1 Targets of MUC Analysis 146......Page 159
7.3 Approaches to Information Extraction in Biology 148......Page 161
7.3.1 Pattern-Matching Approaches 149......Page 162
7.3.3 Full Parsing Approaches 154......Page 167
7.3.5 Mixed Syntax-Semantics Approaches 160......Page 173
7.3.6 Sublanguage-Driven Information Extraction 163......Page 176
7.3.7 Ontology-Driven Information Extraction 166......Page 179
7.4 Conclusion 171......Page 184
References......Page 187
8.1 Introduction 179......Page 192
8.2.1 Literature Databases 180......Page 193
8.2.2 Copyright Issues 181......Page 194
8.3.1 Corpora in Biology 182......Page 195
8.3.2 Collecting MEDLINE Abstracts 183......Page 196
8.3.3 Comparing Corpora 184......Page 197
8.4.1 Annotation for Biomedical Entities 188......Page 201
8.4.2 Annotation for Biological Processes 191......Page 204
8.4.3 Annotation for Linguistic Structure 193......Page 206
8.5.1 Quality Control 195......Page 208
8.5.2 Format of Annotation 199......Page 212
8.5.3 Discontinuous Expressions 202......Page 215
8.6 Annotation Tools 203......Page 216
8.6.1 Reuse of General Purpose Tools 204......Page 217
8.6.2 Corpus Annotation Tools 208......Page 221
References......Page 222
9.1 Introduction 213......Page 226
9.2.1 The Stakeholders 216......Page 229
9.2.2 Dimensions of a Successful Evaluation 217......Page 230
9.2.3 What Can Evaluation Accomplish? 219......Page 232
9.3.1 Biological Applications 220......Page 233
9.4 Current Assessments for Text Mining in Biology 223......Page 236
9.4.1 KDD Challenge Cup 224......Page 237
9.4.2 TREC Genomics Track 227......Page 240
9.4.3 BioCreAtIvE 232......Page 245
9.4.4 BioNLP 239......Page 252
9.5 What Next? 240......Page 253
References......Page 256
10.1 Introduction: Biological Sequence Analysis and  Text Mining 247......Page 260
10.1.1 Improving Homology Searches 250......Page 263
10.1.2 Improving Sequence-Based Functional Classification 253......Page 266
10.2 Gene Expression Analysis and Text Mining 256......Page 269
10.2.1 Assigning Biological Explanations to Gene  Expression Clusters 258......Page 271
10.2.2 Enhancing Expression Data Analysis with  Literature Knowledge 260......Page 273
References......Page 276
Acronyms 267......Page 280
About the Authors 273......Page 286
Index......Page 290