Ontology Alignment Evaluation Initiative - OAEI-2012 Campaign
Preliminary results of MultiFarm here

MultiFarm

The goal of the MultiFarm track is to evaluate the ability of matcher systems to deal with multilingual ontologies. 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), with a special focus on multilingualism.

Evaluation campaign results

The results of the OAEI 2012, for the MultiFarm track are available here.

Data sets

The MultiFarm data set is composed of a set of ontologies translated in different languages and the corresponding alignments between these ontologies. It is based on the OntoFarm dataset, which has been used successfully for several years in the Conference track in the OAEI campaigns. By translating the ontologies of the OntoFarm dataset into eight different languages:

For further information about this dataset, please refer to the dataset description page.

In order to provide some blind evaluation, we do not made available the translations on edas and ekaw ontologies in the current testing data set.

The identifiers of data sets available for testing are given below:

MultiFarm identifiers

The [pair-language] refers to one of the 36 different language pairs: cn-en, cn-cz, cz-es, fr-pt, en-pt, cz-de, pt-ru, cn-pt, cz-ru, de-fr, de-pt, en-es, en-fr, cn-nl, de-ru, cn-de, cn-es, en-nl, cz-en, en-ru, cz-fr, es-ru, de-en, nl-ru, es-pt, de-es, fr-nl, de-nl, nl-pt, es-nl, fr-ru, cz-pt, es-fr, cn-ru, cn-fr, cz-nl. For instance, cn-cz-multifarm, for example, refers to the chinese-czech language pair.

We encourage you to use the Alignment API for manipulating and generating your alignments, and, in particular, for computing evaluation of your results.

Testing your tool

Please, refer to the instructions on how you can test your tools. Following those instructions, you have to use the MultiFarm data set identifiers indicated above.

Contacts

This track is organized by Cassia Trojahn dos Santos, with support of Christian Meilicke. If you have any problems working with the ontologies, any questions or suggestions, feel free to write an email to cassia [.] trojahn [at] irit [.] fr.