Scipediacontent: Scipediacontent moved page Draft Content 590746015 to Shterionov Janssens 2015a

2021-02-02T06:56:10Z

Scipediacontent moved page Draft Content 590746015 to Shterionov Janssens 2015a

Scipediacontent: Created page with " == Abstract == In order to handle real-world problems, state-of-the-art probabilistic logic and learning frameworks, such as ProbLog, reduce the expensive inference to an ef..."

2021-02-02T06:56:06Z

Created page with " == Abstract == In order to handle real-world problems, state-of-the-art probabilistic logic and learning frameworks, such as ProbLog, reduce the expensive inference to an ef..."

New page

== Abstract ==

In order to handle real-world problems, state-of-the-art probabilistic logic and learning frameworks, such as ProbLog, reduce the expensive inference to an efficient Weighted Model Counting. To do so ProbLog employs a sequence of transformation steps, called an \emph{inference pipeline}. Each step in the probabilistic inference pipeline is called a \emph{pipeline component}. The choice of the mechanism to implement a component can be crucial to the performance of the system. In this paper we describe in detail different ProbLog pipelines. Then we perform a empirical analysis to determine which components have a crucial impact on the efficiency. Our results show that the Boolean formula conversion is the crucial component in an inference pipeline. Our main contributions are the thorough analysis of ProbLog inference pipelines and the introduction of new pipelines, one of which performs very well on our benchmarks. ispartof: pages:90-104 ispartof: Practical Aspects of Declarative Languages vol:9131 pages:90-104 ispartof: Practical Aspects of Declarative Languages location:Portland, Oregon, USA date:18 Jun - 19 Jun 2015 status: published

== Original document ==

The different versions of the original document can be found in:

* [https://lirias.kuleuven.be/handle/123456789/500401 https://lirias.kuleuven.be/handle/123456789/500401]

* [http://link.springer.com/content/pdf/10.1007/978-3-319-19686-2_7 http://link.springer.com/content/pdf/10.1007/978-3-319-19686-2_7],
: [http://dx.doi.org/10.1007/978-3-319-19686-2_7 http://dx.doi.org/10.1007/978-3-319-19686-2_7]

* [https://link.springer.com/chapter/10.1007%2F978-3-319-19686-2_7 https://link.springer.com/chapter/10.1007%2F978-3-319-19686-2_7],
: [https://core.ac.uk/display/34635815 https://core.ac.uk/display/34635815],
: [https://research.tilburguniversity.edu/en/publications/implementation-and-performance-of-probabilistic-inference-pipelin https://research.tilburguniversity.edu/en/publications/implementation-and-performance-of-probabilistic-inference-pipelin],
: [http://doi.org/10.1007/978-3-319-19686-2_7 http://doi.org/10.1007/978-3-319-19686-2_7],
: [https://doi.org/10.1007/978-3-319-19686-2_7 https://doi.org/10.1007/978-3-319-19686-2_7],
: [https://dblp.uni-trier.de/db/conf/padl/padl2015.html#ShterionovJ15 https://dblp.uni-trier.de/db/conf/padl/padl2015.html#ShterionovJ15],
: [https://rd.springer.com/chapter/10.1007/978-3-319-19686-2_7 https://rd.springer.com/chapter/10.1007/978-3-319-19686-2_7],
: [https://academic.microsoft.com/#/detail/1144061898 https://academic.microsoft.com/#/detail/1144061898]

← Older revision	Revision as of 06:56, 2 February 2021
(No difference)

Shterionov Janssens 2015a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 590746015 to Shterionov Janssens 2015a

Scipediacontent: Created page with " == Abstract == In order to handle real-world problems, state-of-the-art probabilistic logic and learning frameworks, such as ProbLog, reduce the expensive inference to an ef..."