Probabilistic Description Logics under the Distribution Semantics

Tracking #: 651-1861

Fabrizio Riguzzi
Elena Bellodi
Evelina Lamma
Riccardo Zese

Responsible editor: 
Guest Editors RR2013 Special Issue

Submission type: 
Full Paper
Representing uncertain information is crucial for modeling real world domains. In this paper we present a technique for the integration of probabilistic information in Description Logics (DLs) that is based on the distribution semantics for probabilistic logic programs. In the resulting approach, that we called DISPONTE, the axioms of a probabilistic knowledge base (KB) can be annotated with a real number between 0 and 1. A probabilistic knowledge base then defines a probability distribution over regular KBs called worlds and the probability of a given query can be obtained from the joint distribution of the worlds and the query by marginalization. We present the algorithm BUNDLE for computing the probability of queries from DISPONTE KBs. The algorithm exploits an underlying DL reasoner, such as Pellet, that is able to return explanations for queries. The explanations are encoded in a Binary Decision Diagram from which the probability of the query is computed. The experimentation of BUNDLE shows that it can handle probabilistic KBs of realistic size.
Full PDF Version: 


Solicited Reviews:
Click to Expand/Collapse
Review #1
By Umberto Straccia submitted on 28/Apr/2014
Minor Revision
Review Comment:

The paper addressed almost all my concerns. There are still two issues, one minor and one major.
1. minor issue: correct dl-lite in citation Penaloza, R., Sertkaya, B., 2010a in upper case
2. major issue: I would like to have a guideline to run the experiments. I downloaded the packages, and tried bundle via the GUI. Unluckily, all examples provided under the "esempi" menu, have thrown an exception. I also suggest that you also provide a shell script that allows to run and log the tests you've done.

Review #2
By Claudia d'Amato submitted on 30/Apr/2014
Minor Revision
Review Comment:

The authors addressed almost all the issues raised in the first review.

Authors are invited to put online the datasets (transformed by the authors) and the queries that have been used for experiments in order to allow the repeatability of experiments, also for comparison of related approaches in the future.

Review #3
Anonymous submitted on 30/Apr/2014
Review Comment:

After reviewing the changes made by the authors in the revised version, I confirm that they have adequately addressed all of my comments.