Ontology Alignment Evaluation Initiative - OAEI-2009 Campaign

Benchmark test library

The goal of the benchmark test library is to offer a set of tests which are wide in feature coverage, progressive and stable. It serves the purpose of evaluating the strength and weakness of matchers (by being progressive and wide coverage) and measuring the progress of matchers (by being stable and reusable over the years).

Appart from that, it is made of a set of 111 pairs of ontologies for which the participants have to return an alignment in the alignment format. These results are compared against reference alignments which are available from the beginning.

Data sets

Reference ontology

The domain of this first test is Bibliographic references. It is, of course, based on a subjective view of what must be a bibliographic ontology. There can be many different classifications of publications (based on area, quality, etc.). We choose the one common among scholars based on mean of publications; as many ontologies below (tests #301-304), it is reminiscent to BibTeX.

This reference ontology contains 33 named classes, 24 object properties, 40 data properties, 56 named individuals and 20 anonymous individuals.

The complete ontology is that of test #101.

The reference ontology is based on the one of the first EON Ontology Alignment Contest. It is improved by comprising a number of circular relations that were missing from the first test. In 2006, we have put the UTF-8 version of the tests as standard, the ISO-8859-1 being optional. In 2007, the tests are the same as in 2006.

The reference ontology is put in the context of the semantic web by using other external resources for expressing non bibliographic information. It takes advantage of FOAF (http://xmlns.com/foaf/0.1/) and iCalendar (http://www.w3.org/2002/12/cal/) for expressing the People, Organization and Event concepts. Here are the external reference used:

• http://www.w3.org/2002/12/cal/#:Vevent (defined in http://www.w3.org/2002/12/cal/ical.n3 and supposedly in http://www.w3.org/2002/12/cal/ical.rdf)
• http://xmlns.com/foaf/0.1/#:Person (defined in http://xmlns.com/foaf/0.1/index.rdf)
• http://xmlns.com/foaf/0.1/#:Organization (defined in http://xmlns.com/foaf/0.1/index.rdf)

This reference ontology is a bit limited in the sense that it does not contain attachement to several classes.

Similarly the kind of proposed alignments is still limited: they only match named classes and properties, they mostly use the "=" relation with confidence of 1.

The ontologies are described in OWL-DL and serialized in the RDF/XML format.

Tests at a glance

The tests are systematically generated to as to start from some reference ontology and discarding a number of information in order to evaluate how the algorithm behave when this information is lacking.

Test numbering (almost) fully preserves the numbering of the first EON contest.

The table below summarize what has been retracted from the reference ontology. There are here 6 catagories of alteration:

Name

Name of entities that can be replaced by (R/N) random strings, (S)ynonyms, (N)ame with different conventions, (F) strings in another language than english.

Comments

Comments can be (N) suppressed or (F) translated in another language.

Specialization Hierarchy

can be (N) suppressed, (E)xpansed or (F)lattened.

Instances

can be (N) suppressed

Properties

can be (N) suppressed or (R) having the restrictions on classes discarded.

Classes

can be (E)xpanded, i.e., relaced by several classes or (F)latened.

These transformations generate the set of tests displayed below with their derivation relations. The upper the test, the easier it is supposed to be.

Alignments

Below are provided the set of tests with expected alignments in the Alignment format described here. Each ontology is to be aligned with the reference ontology (i.e., that of test #101).

The only interesting alignments are those involving classes and properties of the given ontologies. So the alignments should not align individuals, nor entities from the external ontologies.

There is some chance that the final test be improved by adding entity expansion and reduction. It is also possible that there will be a lot of more instances in each ontology.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

NOTE: The onto.rdf file is provided for compatibility purposes. However, it is possible to run the test directly on the true file, i.e., http://www.w3.org/TR/2003/PR-owl-guide-20031209/wine. Indeed, wine imports food which imports wine and some parsers do not realize that onto.rdf is the same ontology as wine.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]
Alignment : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]

NOTE: You can use alternatively the ISO-Latin-1 (ISO-8859-1) version of the tests by renaming them after their UTF-8 version.

Ontology : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]
Alignment : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]

NOTE: You can use alternatively the ISO-Latin-1 (ISO-8859-1) version of the tests by renaming them after their UTF-8 version.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]
Alignment : [RDF/XML] [RDF/XML in ISO-8859-1] [HTML]

NOTE: You can use alternatively the ISO-Latin-1 (ISO-8859-1) version of the tests by renaming them after their UTF-8 version.

Ontology : [RD/XML] [HTML]
Alignment : [RDF/XML] [HTML]

(variation: compile inheritance)

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

The alignment here contains relations which are not "=" but "<".

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

(variation: no property nor global restrictions on properties)

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

(variation: leave the properties in instances)

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Here one limitation of the proposed format is that it does not cover alignments such as: journalName = name o journal.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Note that the 3xx tests are only here for comparability with previous years. We know that the reference alignments for these tests are not perfect (especially because the ontologies sometimes contain flaws).

For a computer scientist, BibTeX is the starting point for a useful bibliographic ontology. It is of wide use and relatively well thought out. This ontology can be found at and is documented in BibTex in OWL.

This is a test of comparing our test ontology with an actual ontology, simpler and closer to the initial BibTeX ontology. The alignment result contains some inclusion (<) alignment relations.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

This ontology is very similar to the previous one, even closer to the genuine BibTeX, with different extensions and naming conventions. It can be found at http://ebiquity.umbc.edu.

The alignment result also contains some inclusion (<) alignment relations.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

The Karlsruhe ontology (http://www.aifb.uni-karlsruhe.de/ontology) is used in the Ontoweb portal. It is a refinement from other ontologies such as (KA)². As such it does not only defines bibliographic items but many other items.

The alignment contains < as well as > relations.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

This INRIA ontology (fr.inrialpes.exmo.rdf.bib.owl) has been designed by Antoine Zimmermann from the BibTeX in OWL ontology and our Bibliographic XML DTD. Its goal was to gather easily a number of RDF items. These items were BibTeX entries found on the web and transformed in RDF according to this ontology.

The actual hierarchy of this ontology contains classes which are subclasses of several other classes.

Ontology : [RDF/XML] [HTML]
Alignment : [RDF/XML] [HTML]

Versions

The release notes of the previous test versions used in the OAEI-2009 can be found here.

Modalities

The test set is made of a set of directories (one per test) containing an ontology (onto.rdf) in OWL. Participants must match each of these ontologies with the ontology found in 101/onto.rdf and output the resulting alignment, in the alignment format, in a file participant.rdf in the same directory (participant is replaced by the name of the system: no more than 8 alphanumeric characters, lowercase).

The test set also contains the reference alignments against which the results will be evaluated. It is, of course, forbiden to use any for there results for performing the matching task.

The resulting alignments in the same directory structure can be zipped (please, zipped) and sent to the organisers.

Schedule

The schedule is that of http://oaei.ontologymatching.org/2009/.

Tools

A zip file contains all the data about the test. That is:

• This web page;
• All ontology/alignment pairs in OWL/RDF/XML;
• The prior known alignments in RDF/XML;
• All ontology/alignment pairs in HTML;
• XSLT stylesheet from ontologies and alignment to HTML;
• The provided expected alignments in RDF/XML (for the systematic benchmark);
• A directory with some reference ontologies (iCal, Foaf);

We would like to find a simple converter from OWL/XML/RDF to N3 (and maybe RDFS).

You can use the Alignment API for manipulating and generating your alignments (in particular for computing evaluation of your results).

Acknowledgements

Many resources have been used for setting up this test (I must put links):

• BibTeX
• UMBC BibTeX
• MIT BibTex
• Java BibTeX parser
• Karlsruhe ontology and bibtex to RDF translator that we adapted
• INRIA's adaptation of the ontologies and the translator above by Antoine Zimmermann.
• Lockheed evaluation format.
• WonderWeb/Manchester's OWL species validator

Various people helped testing or suggested improvements and tests:

• York Sure and Oscar Corcho for welcoming this at their EON workshop;
• Heiner Stuckenschmidt helped providing several sorts of tests;
• Liz Palmer proposed variation tests;
• Natasha Noy and David Loup have been very helpful in noticing and correcting bugs.
• Raphaël Troncy helped debug the 2005 version of these tests.
• Sławomir Niedbała, Guillermo Nudelman Hess, Alfio Ferrara, Sabine Massmann and Wei Hu suggested even more precise corrections in 2006.
• Christian Meilicke offered some criticism on the 3xx test series.
• Jérôme David drew the lattice of tests.

Contacts

Contact address is Jerome : Euzenat # inrialpes : fr