Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning)

Cover......Page 1
Introduction to Statistical Relational Learning......Page 4
Copyright - ISBN: 9780262072885......Page 5
Contents......Page 6
Series Foreword......Page 12
Preface......Page 14
1.1 Overview......Page 16
1.2 Brief History of Relational Learning......Page 17
1.4 Statistical Relational Learning......Page 18
1.5 ChapterMap......Page 20
1.6 Outlook......Page 23
2.1 Introduction......Page 28
2.2 Representation......Page 29
2.3 Inference......Page 37
2.4 Learning......Page 57
2.5 Conclusion......Page 69
3.1 Introduction......Page 72
3.2 Logic Programming......Page 73
3.3 Inductive Logic Programming: Settings and Approaches......Page 79
3.4 Relational Classification Rules......Page 86
3.5 Relational Decision Trees......Page 90
3.6 Relational Association Rules......Page 95
3.7 Relational Distance-BasedMethods......Page 99
3.8 Recent Trends in ILP and RDM......Page 104
4.1 Introduction......Page 108
4.2 GraphicalModels......Page 109
4.3 Linear-Chain Conditional Random Fields......Page 115
4.4 CRFs in General......Page 123
4.5 Skip-Chain CRFs......Page 131
4.6 Conclusion......Page 137
5.1 Introduction......Page 144
5.2 PRMRepresentation......Page 145
5.3 The Difference between PRMs and Bayesian Networks......Page 155
5.5 Probabilistic Model of Link Structure......Page 156
5.6 PRMs with Class Hierarchies......Page 166
5.7 Inference in PRMs......Page 174
5.8 Learning......Page 176
5.9 Conclusion......Page 188
6.1 Introduction......Page 190
6.2 Relational Classification and Link Prediction......Page 192
6.3 Graph Structure and Subgraph Templates......Page 193
6.4 Undirected Models for Classification......Page 195
6.5 Learning theModels......Page 199
6.6 Experimental Results......Page 202
6.7 Discussion and Conclusions......Page 212
7.1 Introduction......Page 216
7.2 Background: Graphical Models......Page 217
7.3 The Basic Ideas......Page 219
7.4 Probabilistic Entity-Relationship Models......Page 225
7.5 PlateModels......Page 241
7.6 Probabilistic Relational Models......Page 243
7.7 Technical Details......Page 244
7.8 Extensions and Future Work......Page 248
8.1 Introduction......Page 254
8.2 Dependency Networks......Page 257
8.3 Relational Dependency Networks......Page 258
8.4 Experiments......Page 267
8.5 Related Work......Page 277
8.6 Discussion and Future Work......Page 279
9.1 Introduction......Page 284
9.2 Representation......Page 286
9.3 Inference......Page 293
9.4 Learning......Page 296
9.5 Conclusion......Page 302
10.1 Introduction......Page 306
10.2 On Bayesian Networks and Logic Programs......Page 308
10.3 Bayesian Logic Programs......Page 311
10.4 Extensions of the Basic Framework......Page 319
10.5 Learning Bayesian Logic Programs......Page 326
10.7 Related Work......Page 330
10.8 Conclusions......Page 333
11.1 Introduction......Page 338
11.2 Mixing Deterministic and Probabilistic Choice......Page 339
11.3 Stochastic Grammars......Page 345
11.4 Stochastic Logic Programs......Page 348
11.5 Learning Techniques......Page 350
11.6 Conclusion......Page 352
12.1 The Need for a Unifying Framework......Page 354
12.2 Markov Networks......Page 356
12.3 First-Order Logic......Page 357
12.4 Markov Logic......Page 359
12.5 SRL Approaches......Page 365
12.6 SRL Tasks......Page 369
12.7 Inference......Page 371
12.8 Learning......Page 373
12.9 Experiments......Page 375
12.10 Conclusion......Page 382
13.1 Introduction......Page 388
13.2 Examples......Page 390
13.3 Syntax and Semantics: Possible Worlds......Page 393
13.4 Syntax and Semantics: Probabilities......Page 398
13.6 Inference......Page 403
13.7 Related Work......Page 408
13.8 Conclusions and Future Work......Page 409
14.1 Introduction......Page 414
14.2 The IBAL Language......Page 416
14.3 Examples......Page 422
14.4 Semantics......Page 426
14.5 Desiderata for Inference......Page 430
14.6 Related Approaches......Page 431
14.7 Inference......Page 434
14.8 Lessons Learned and Conclusion......Page 444
15.1 Introduction......Page 448
15.2 Language, Semantics and Inference problem......Page 450
15.3 The First-Order Variable Elimination (FOVE) algorithm......Page 452
15.4 An experiment......Page 459
15.5 Auxiliary operations......Page 461
15.6 Applicability of lifted inference......Page 463
15.8 Conclusion......Page 464
16.1 Introduction......Page 468
16.2 DetailedMethodology......Page 473
16.3 Experimental Evaluation......Page 478
16.4 RelatedWork and Discussion......Page 486
16.5 Conclusion......Page 487
17.1 Introduction......Page 492
17.2 View Learning forMammography......Page 493
17.3 Naive View Learning Framework......Page 497
17.4 Initial Experiments......Page 498
17.5 Integrated View Learning Framework......Page 505
17.6 Further Experiments and Results......Page 506
17.7 RelatedWork......Page 508
17.8 Conclusions and FutureWork......Page 509
18.1 Introduction......Page 514
18.2 ProblemSetup......Page 517
18.3 Approximate Policy Iteration with a Policy Language Bias......Page 518
18.4 API for Relational Planning......Page 522
18.5 Bootstrapping......Page 531
18.6 Relational Planning Experiments......Page 535
18.7 RelatedWork......Page 542
18.8 Summary and FutureWork......Page 545
19.1 Introduction......Page 550
19.2 Background on Natural Language Processing......Page 551
19.3 Information Extraction......Page 552
19.4 Collective Information Extraction with RMNs......Page 553
19.5 Future Research on SRL for NLP......Page 564
19.6 Conclusions......Page 565
20.1 Introduction......Page 568
20.2 The Relational Inference Problem......Page 571
20.3 Integer Linear Programming Inference......Page 575
20.4 Solving Integer Linear Programming......Page 577
20.5 Experiments......Page 578
20.6 Comparison with Other Inference Methods......Page 585
20.7 Conclusion......Page 591
Contributors......Page 596
Index......Page 602