Introduction to Statistical Relational Learning

Transcription

1 Introduction to Statistical Relational Learning

2 Series Foreword Preface xi xiii 1 Introduction 1 Lise Getoor, Ben Taskar 1.1 Overview Brief History of Relational Learning Emerging Trends Statistical Relational Learning Chapter Map Outlook 8 2 Graphical Models in a Nutshell 13 Daphne Koller, Nir Friedman, Lise Getoor, Ben Taskar 2.1 Introduction Representation Inference Learning Conclusion 54 3 Inductive Logic Programming in a Nutshell 57 Saso Dzeroski 3.1 Introduction Logic Programming Inductive Logic Programming: Settings and Approaches Relational Classification Rules...c Relational Decision Trees Relational Association Rules Relational Distance-Based Methods Recent Trends in ILP and RDM 89 4 An Introduction to Conditional Random Fields for Relational Learning 93 Charles Sutton, Andrew McCallum 4.1 Introduction Graphical Models Linear-Chain Conditional Random Fields CRFs in General Skip-Chain CRFs Conclusion 122

3 vi 5 Probabilistic Relational Models 129 Lise Getoor, Nir Friedman, Daphne Koller, Avi Pfeffer, Ben Taskar 5.1 Introduction PRM Representation The Difference between PRMs and Bayesian Networks PRMs with Structural Uncertainty Probabilistic Model of Link Structure PRMs with Class Hierarchies Inference in PRMs Learning Conclusion Relational Markov Networks 175 Ben Taskar, Pieter Abbeel, Ming-Fai Wong, Daphne Koller 6.1 Introduction Relational Classification and Link Prediction Graph Structure and Subgraph Templates Undirected Models for Classification Learning the Models Experimental Results Discussion and Conclusions Probabilistic Entity-Relationship Models, PRMs, and Plate Models 201 David Heckerman, Chris Meek, Daphne Koller 7.1 Introduction Background: Graphical. Models The Basic Ideas Probabilistic Entity-Relationship Models Plate Models Probabilistic Relational Models Technical Details Extensions and Future Work Relational Dependency Networks 239 Jennifer Neville, David Jensen 8.1 Introduction Dependency Networks Relational Dependency Networks Experiments Related Work Discussion and Future Work Logic-based Formalisms for Statistical Relational Learning 269 James Ciissens 9.1 Introduction Representation Inference Learning Conclusion Bayesian Logic Programming: Theory and Tool 291 Kristian Kersting, Luc De Raedt

4 10.1 Introduction On Bayesian Networks and Logic Programs Bayesian Logic Programs Extensions of the Basic Framework Learning Bayesian Logic Programs BALIOS - The Engine for Basic Logic Programs Related Work Conclusions Stochastic Logic Programs: A Tutorial 323 Stephen Muggleton, Niels Pahlavi 11.1 Introduction Mixing Deterministic and Probabilistic Choice Stochastic Grammars Stochastic Logic Programs Learning Techniques Conclusion Markov Logic: A Unifying Framework for Statistical Relational Learning 339 Pedro Domingos, Matthew Richardson 12.1 The Need for a Unifying Framework Markov Networks First-Order Logic Markov Logic SRL Approaches SRL Tasks Inference Learning Experiments Conclusion BLOG: Probabilistic Models with Unknown Objects 373 Brian Milch, Bhaskara Marthi, Stuart Russell, David Sontag, Daniel L. Ong, Andrey Kolobov 13.1 Introduction " Examples " Syntax and Semantics: Possible Worlds Syntax and Semantics: Probabilities Evidence and Queries Inference..* Related Work Conclusions and Future Work The Design and Implementation of IBAL: A General-Purpose Probabilistic Language 399 Avi Pfeffer 14.1 Introduction The IBAL Language Examples Semantics Desiderata for Inference Related Approaches Inference 419

5 viii 14.8 Lessons Learned and Conclusion, Lifted First-Order Probabilistic Inference 433 Rodrigo de Salvo Braz, Eyal Amir, Dan Roth 15.1 Introduction Language, Semantics and Inference problem The First-Order Variable Elimination (FOVE) algorithm An experiment Auxiliary operations Applicability of lifted inference Future Directions Conclusion Feature Generation and Selection in Multi-Relational Statistical Learning 453 Alexandrin Popescul, Lyle H. Ungar 16.1 Introduction Detailed Methodology Experimental Evaluation Related Work and Discussion Conclusion Learning a New View of a Database: With an Application in Mammography 477 Jesse Davis, Elizabeth Burnside, Ines Dutra, David Page, Raghu Ramakrishnan, Jude Shavlik, Vitor Santos Costa 17.1 Introduction View Learning for Mammography Naive View Learning Framework Initial Experiments Integrated View Learning Framework Further, Experiments and Results Related Work Conclusions and Future Work Reinforcement Learning in Relational Domains: A Policy-Language Approach 499 Alan Fern, SungWook Yoon, Robert Givan 18.1 Introduction Problem Setup Approximate Policy Iteration with a Policy Language Bias API for Relational Planning Bootstrapping Relational Planning Experiments Related Work Summary and Future Work Statistical Relational Learning for Natural Language Information Extraction 535 ' Razvan C. Bunescu, Raymond J. Mooney 19.1 Introduction Background on Natural Language Processing Information Extraction Collective Information Extraction with RMNs Future Research on SRL for NLP »Conclusions 550

6 20 Global Inference for Entity and Relation Identification via a Linear Programming Formulation 553 Dan Roth, Wen-tau Yih 20.1 Introduction The Relational Inference Problem Integer Linear Programming Inference Solving Integer Linear Programming Experiments Comparison with Other Inference Methods Conclusion 576 Contributors 581 Index 587