%0 Conference Paper %1 Suchanek:2007:YCS:1242572.1242667 %A Suchanek, Fabian M. %A Kasneci, Gjergji %A Weikum, Gerhard %B Proceedings of the 16th international conference on World Wide Web %C New York, NY, USA %D 2007 %I ACM %K dbpedia ontologies semantic_Web yago %P 697--706 %T Yago: a core of semantic knowledge %U http://doi.acm.org/10.1145/1242572.1242667 %X We present YAGO, a light-weight and extensible ontology with high coverage and quality. YAGO builds on entities and relations and currently contains more than 1 million entities and 5 million facts. This includes the Is-A hierarchy as well as non-taxonomic relations between entities (such as HASONEPRIZE). The facts have been automatically extracted from Wikipedia and unified with WordNet, using a carefully designed combination of rule-based and heuristic methods described in this paper. The resulting knowledge base is a major step beyond WordNet: in quality by adding knowledge about individuals like persons, organizations, products, etc. with their semantic relationships - and in quantity by increasing the number of facts by more than an order of magnitude. Our empirical evaluation of fact correctness shows an accuracy of about 95%. YAGO is based on a logically clean model, which is decidable, extensible, and compatible with RDFS. Finally, we show how YAGO can be further extended by state-of-the-art information extraction techniques.

@inproceedings{Suchanek:2007:YCS:1242572.1242667, abstract = {We present YAGO, a light-weight and extensible ontology with high coverage and quality. YAGO builds on entities and relations and currently contains more than 1 million entities and 5 million facts. This includes the Is-A hierarchy as well as non-taxonomic relations between entities (such as HASONEPRIZE). The facts have been automatically extracted from Wikipedia and unified with WordNet, using a carefully designed combination of rule-based and heuristic methods described in this paper. The resulting knowledge base is a major step beyond WordNet: in quality by adding knowledge about individuals like persons, organizations, products, etc. with their semantic relationships - and in quantity by increasing the number of facts by more than an order of magnitude. Our empirical evaluation of fact correctness shows an accuracy of about 95%. YAGO is based on a logically clean model, which is decidable, extensible, and compatible with RDFS. Finally, we show how YAGO can be further extended by state-of-the-art information extraction techniques.}, added-at = {2013-06-29T10:48:26.000+0200}, address = {New York, NY, USA}, author = {Suchanek, Fabian M. and Kasneci, Gjergji and Weikum, Gerhard}, biburl = {https://www.bibsonomy.org/bibtex/20f999818af6ccb87040e3416bb346e51/lysander07}, booktitle = {Proceedings of the 16th international conference on World Wide Web}, description = {Yago}, interhash = {1d2c2b23ce2a6754d12c4364e19c574c}, intrahash = {0f999818af6ccb87040e3416bb346e51}, keywords = {dbpedia ontologies semantic_Web yago}, pages = {697--706}, publisher = {ACM}, series = {WWW '07}, timestamp = {2013-06-29T10:48:27.000+0200}, title = {Yago: a core of semantic knowledge}, url = {http://doi.acm.org/10.1145/1242572.1242667}, year = 2007 }