Ontology-Mediated Query Answering over Log-Linear Probabilistic Data

Authors: Stefan Borgwardt, İsmail İlkan Ceylan, Thomas Lukasiewicz2711-2718

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We propose a new data model that integrates the paradigm of ontology-mediated query answering with probabilistic databases, employing a log-linear probability model. We compare our approach to existing proposals, and provide supporting computational results. and We obtain a host of complexity results.
Researcher Affiliation Academia Stefan Borgwardt Faculty of Computer Science Technische Universit at Dresden, Germany stefan.borgwardt@tu-dresden.de Ismail Ilkan Ceylan, Thomas Lukasiewicz Department of Computer Science University of Oxford, UK ismail.ceylan@cs.ox.ac.uk thomas.lukasiewicz@cs.ox.ac.uk
Pseudocode No The paper describes theoretical models and reductions but does not include any pseudocode or algorithm blocks.
Open Source Code No We leave as future work an implementation, combining existing gradient-based optimization methods with efficient rewriting techniques and PDB or MLN inference engines.
Open Datasets No The paper is theoretical and does not conduct empirical experiments with a training dataset. It references existing probabilistic knowledge bases as sources for data for a theoretical learning approach, but not for empirical training.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments, therefore no training/validation/test splits are provided.
Hardware Specification No The paper is theoretical and does not describe experimental hardware specifications.
Software Dependencies No The paper is theoretical and explicitly states that implementation is future work, therefore no specific software dependencies with version numbers are provided.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details or hyperparameters.