Domingos P., Lowd D. Markov Logic: An Interface Layer for Artificial Intelligence

Series: Synthesis Lectures on Artificial Intelligence and Machine Learning.
— Morgan and Claypool Publishers, 2009. — 145 p. — ISBN: 978-1598296921, e-ISBN: 978-1598296938.Most subfields of computer science have an interface layer via which applications communicate with the infrastructure, and this is key to their success (e.g., the Internet in networking, the relational model in databases, etc.). So far this interface layer has been missing in AI. First-order logic and probabilistic graphical models each have some of the necessary features, but a viable interface layer requires combining both. Markov logic is a powerful new language that accomplishes this by attaching weights to first-order formulas and treating them as templates for features of Markov random fields. Most statistical models in wide use are special cases of Markov logic, and first-order logic is its infinite-weight limit. Inference algorithms for Markov logic combine ideas from satisfiability, Markov chain Monte Carlo, belief propagation, and resolution. Learning algorithms make use of conditional likelihood, convex optimization, and inductive logic programming. Markov logic has been successfully applied to problems in information extraction and integration, natural language processing, robot mapping, social networks, computational biology, and others, and is the basis of the open-source Alchemy system.The Interface Layer
What Is the Interface Layer for AI?
Markov Logic and Alchemy: An Emerging Solution
Overview of the Book
Markov Logic
First-Order Logic
Markov Networks
Markov Logic
Relation to Other Approaches
Inference
Inferring the Most Probable Explanation
Computing Conditional Probabilities
Lazy Inference
Lifted Inference
Learning
Weight Learning
Structure Learning and Theory Revision
Unsupervised Learning
Transfer Learning
Extensions
Continuous Domains
Infinite Domains
Recursive Markov Logic
Relational Decision Theory
Applications
Collective Classification
Social Network Analysis and Link Prediction
Entity Resolution
Information Extraction
Unsupervised Coreference Resolution
Robot Mapping
Link-based Clustering
Semantic Network Extraction from TextA The Alchemy System
A.1 Input Files
A.2 Inference
A.3 Weight Learning
A.4 Structure Learning