Abstract | ||
---|---|---|
We present YAGO2, an extension of the YAGO knowledge base, in which entities, facts, and events are anchored in both time and space. YAGO2 is built automatically from Wikipedia, GeoNames, and WordNet. It contains 447 million facts about 9.8 million entities. Human evaluation confirmed an accuracy of 95% of the facts in YAGO2. In this paper, we present the extraction methodology, the integration of the spatio-temporal dimension, and our knowledge representation SPOTL, an extension of the original SPO-triple model to time and space. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.artint.2012.06.001 | Artif. Intell. |
Keywords | Field | DocType |
extraction methodology,million fact,original spo-triple model,spatio-temporal dimension,million entity,knowledge representation spotl,temporally enhanced knowledge base,human evaluation,yago knowledge base,information extraction,ontologies | Ontology (information science),Knowledge representation and reasoning,Information retrieval,Computer science,Spacetime,Information extraction,Knowledge base,WordNet | Journal |
Volume | Issue | ISSN |
194, | 1 | 0004-3702 |
Citations | PageRank | References |
462 | 13.57 | 73 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Johannes Hoffart | 1 | 1362 | 52.62 |
Fabian M. Suchanek | 2 | 3900 | 188.75 |
Klaus Berberich | 3 | 1271 | 68.96 |
Gerhard Weikum | 4 | 12710 | 2146.01 |