PARIS - Probabilistic Alignment of Relations, Instances, and Schema

A project of the Webdam team at INRIA Saclay

PARIS

PARIS is a system for the automatic alignment of RDF ontologies. PARIS aligns not only instances, but also relations and classes. Alignments at the instance level cross-fertilize with alignments at the schema level. Thereby, our system provides a truly holistic solution to the problem of ontology alignment. The heart of the approach is probabilistic, i.e., we measure degrees of matchings based on probability estimates. This allows PARIS to run without parameter tuning. Experiments show that PARIS obtains a precision of around 90% in experiments with some of the world’s largest ontologies.

Contributors

PARIS is a project of the Webdam team at INRIA Saclay. The main contributors are:

Publications

Our main paper is:

Fabian M. Suchanek, Serge Abiteboul, Pierre Senellart
"PARIS: Probabilistic Alignment of Relations, Instances, and Relations" (pdf, bib)
38th International Conference on Very Large Databases (VLDB 2012)
PVLDB Journal, Volume 5, Number 3, November 2011.

Recent developments around PARIS are also discussed as part of the following article:

Antoine Amarilli, Luis Galárraga, Nicoleta Preda, Fabian M. Suchanek
"Recent Research Topics around the YAGO Knowledge Base" (PDF)
invited paper at the Asia Pacific Web Conference (APWEB)

Another paper using PARIS:

Marilena Oita, Antoine Amarilli, Pierre Senellart
"Cross-Fertilizing Deep Web Analysis and Ontology Enrichment" (pdf, bib)
Second International Workshop on Searching and Integrating New Web Data Sources (VLDS 2012)
More documentation is available:

Downloads

All material here is made available under a Creative Commons Attribution Non-commercial License, unless covered by other licenses.
Code: Documentation:

We have tried out PARIS on several datasets (see our paper). These are:

Mappings YAGO/DBpedia

We provide here the mappings between the concepts, instances and relations of YAGO and DBpedia, as computed by PARIS.

Feedback

For any feedback or questions, please contact one of the authors. Technical inquiries should be addressed in priority to Fabian Suchanek (firstName@lastName.name) and Antoine Amarilli (a3nmNOSPAM@a3nm.net).