Name
Abstract | ||
|---|---|---|
Markov logic, as a highly expressive representation formalism that essentially combines the semantics of probabilistic graphical models with the full power of first-order logic, is one of the most intriguing representations in the field of probabilistic logical modelling. However, as we will show, models in Markov logic often fail to generalize because the parameters they contain are highly domain-specific. We take the perspective of generative stochastic processes in order to describe probability distributions in relational domains and illustrate the problem in this context by means of simple examples.We propose an extension of the language that involves the specification of a priori independent attributes and that furthermore introduces a dynamic parameter adjustment whenever a model in Markov logic is instantiated for a certain domain (set of objects). Our extension removes the corresponding restrictions on processes for which models can be learned using standard methods and thus enables Markov logic networks to be practically applied to a far greater class of generative stochastic processes. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-74565-5_12 | KI |
Keywords | Field | DocType |
relational domains,certain domain,generative stochastic process,model probability distributions,probabilistic graphical model,markov logic network,expressive representation formalism,extending markov logic,probabilistic logical modelling,first-order logic,markov logic,dynamic parameter adjustment,corresponding restriction,stochastic process,probabilistic logic,probability distribution,first order logic | Markov process,Markov model,Markov chain,Multimodal logic,Description logic,Algorithm,Probabilistic CTL,Variable-order Markov model,Probabilistic logic,Mathematics | Conference |
Volume | ISSN | Citations |
4667 | 0302-9743 | 12 |
PageRank | References | Authors |
0.85 | 7 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dominik Jain | 1 | 157 | 10.30 |
| Bernhard Kirchlechner | 2 | 107 | 7.57 |
| Michael Beetz | 3 | 3784 | 284.03 |