ProbLog2: From Probabilistic Programming to Statistical Relational Learning
Joris Renkens, Dimitar Shterionov, Guy Van den Broeck, Jonas Vlasselaer, Daan Fierens, Wannes Meert, Gerda Janssens, Luc De Raedt · Lirias (KU Leuven) · 2012
ProbLog is a probabilistic programming language based on Prolog. The new ProbLog system- called ProbLog2- can solve a range of inference and learning tasks typical for the Probabilistic Graphical Models (PGM) and Statistical Rela-tional Learning (SRL) communities. The main mechanism behind ProbLog2 is a conversion of the given program to a weighted Boolean formula. We argue that this conversion approach can also be applied- with certain restrictions- to other probabilistic programming languages such as Church and Figaro. 1