Towards an Automatic Creation of Localized Versions of DBpedia Alessio Palmero Aprosio 1 , Claudio Giuliano 2 , and Alberto Lavelli 2 1 Università degli Studi di Milano, via Comelico 39/41, 20135 Milano, Italy alessio.palmero@unimi.it 2 Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy {giuliano,lavelli}@fbk.eu Abstract. DBpedia is a large-scale knowledge base that exploits Wikipedia as primary data source. The extraction procedure requires to manually map Wikipedia infoboxes into the DBpedia ontology. Thanks to crowdsourcing, a large number of infoboxes has been mapped in the English DBpedia. Conse- quently, the same procedure has been applied to other languages to create the localized versions of DBpedia. However, the number of accomplished mappings is still small and limited to most frequent infoboxes. Furthermore, mappings need maintenance due to the constant and quick changes of Wikipedia articles. In this paper, we focus on the problem of automatically mapping infobox attributes to properties into the DBpedia ontology for extending the coverage of the existing localized versions or building from scratch versions for languages not covered in the current version. The evaluation has been performed on the Italian map- pings. We compared our results with the current mappings on a random sample re-annotated by the authors. We report results comparable to the ones obtained by a human annotator in term of precision, but our approach leads to a significant improvement in recall and speed. Specifically, we mapped 45,978 Wikipedia in- fobox attributes to DBpedia properties in 14 different languages for which map- pings were not yet available. The resource is made available in an open format. 1 Introduction DBpedia is a community project 1 aiming to develop a large-scale knowledge base that exploits Wikipedia as primary data source. Wikipedia represents a practical choice as it is freely available under Creative Commons License, covers an extremely large part of human knowledge in different languages (45 out of 285 have more than 100,000 articles), and is populated by more than 100,000 active contributors, ensuring that the information contained is constantly updated and verified. At the time of starting this paper, the English DBpedia contained about 3.77 million entities, out of which 2.35 millions are classified in the DBpedia Ontology, available as Linked Data, 2 and via DBpedia’s main SPARQL endpoint. 3 Due to the large and constantly increasing number 1 http://dbpedia.org/ 2 http://wiki.dbpedia.org/Downloads 3 http://dbpedia.org/sparql H. Alani et al. (Eds.): ISWC 2013, Part I, LNCS 8218, pp. 494–509, 2013. c  Springer-Verlag Berlin Heidelberg 2013