Ontology Alignment Evaluation Initiative - The OAEI 2016 Campaign

OAEI 2016::Instance Matching Track

The Instance Matching Track aims at evaluating the performance of matching tools when the goal is to detect the degree of similarity between pairs of items/instances expressed in the form of OWL Aboxes.

The track is organized in the following three independent tasks, namely:

The datasets corresponding to the three tasks will be available from June 10th 2016 and frozen by June 30th 2016.. A detailed task description will be also provided in terms of expected results and data-format required.

To participate to the Instance Matching Track, submit results related to one, more, or even all the expected tasks.

Task description

SABINE Task (show/hide results)

SABINE is a modular benchmark in the domain of European politics for Social Business Intelligence (SBI). SABINE includes an ontology with 500 topics, both in English and Italian languages, and corresponding mappings to DBPedia.

SABINE sub-tasks

Download datasets: Inter-linguistic mapping, Data linking

Contact: Alfio Ferrara (alfio.ferrara@unimi.it) and Stefano Montanelli (stefano.montanelli@unimi.it).

SYNTHETIC Task (show/hide results)

The datasets are produced by altering a set of original data through value-based, structure-based, and semantics-aware transformations (simple combination of transformations).

The datasets of the first task is generated and transformed using SPIMBENCH and the datasets of the second task is generated using UOBM and transformed using LANCE.

Even though the transformation categories are the same for both tasks, we expect the IM systems to return interesting results and thus allow us to understand how the aspect of the structure of the data affects the matchings.

SYNTHETIC sub-tasks

Download datasets: Datasets

Contact: Tzanina Saveta (jsaveta@ics.forth.gr) and Irini Fundulaki (fundul@ics.forth.gr).

DOREMUS Task (show/hide results)

The DOREMUS task contains real world data coming from two major French cultrual institutions: the French National Library (BnF) and the Philharmonie de Paris (PP). The data are about classical music works and follow the DOREMUS model (one single vocabulary for both datasets) issued from the DOREMUS project (www.doremus.org). The properties describing these works are, to name a few, the name of the composer, the title(s) of the work, its genre and instruments, etc. We have selected works described both at the BnF and at the PP with different degrees of heterogeneity in their descriptions.

DOREMUS sub-tasks

Download datasets: DOREMUS tasks

Contact: Konstantin Todorov (todorov@lirmm.fr) and Manel Achichi (achichi@lirmm.fr)