@inproceedings{suchanek2007semantic, 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.}, acmid = {1242667}, address = {New York, NY, USA}, author = {Suchanek, Fabian M. and Kasneci, Gjergji and Weikum, Gerhard}, booktitle = {Proceedings of the 16th international conference on World Wide Web}, doi = {10.1145/1242572.1242667}, interhash = {1d2c2b23ce2a6754d12c4364e19c574c}, intrahash = {84ae693c0a6dfb6d4b051b0b6dbd3668}, isbn = {978-1-59593-654-7}, location = {Banff, Alberta, Canada}, numpages = {10}, pages = {697--706}, publisher = {ACM}, title = {YAGO: a core of semantic knowledge}, url = {http://doi.acm.org/10.1145/1242572.1242667}, year = 2007 }