YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia

Johannes Hoffart; Fabian M. Suchanek; Klaus Berberich; Gerhard Weikum

doi:10.1016/j.artint.2012.06.001

YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia

Johannes Hoffart, Fabian M. Suchanek, Klaus Berberich, Gerhard Weikum

Research output: Contribution to journal › Article › peer-review

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.

Original language	English
Pages (from-to)	28-61
Number of pages	34
Journal	Artificial Intelligence
Volume	194
DOIs	https://doi.org/10.1016/j.artint.2012.06.001
Publication status	Published - 1 Jan 2013
Externally published	Yes

Keywords

Information extraction
Knowledge bases
Ontologies
Spatio-temporal facts

Access to Document

10.1016/j.artint.2012.06.001

Cite this

@article{070c2055fe8e4f989f46bcbac55ce388,

title = "YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia",

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.",

keywords = "Information extraction, Knowledge bases, Ontologies, Spatio-temporal facts",

author = "Johannes Hoffart and Suchanek, \{Fabian M.\} and Klaus Berberich and Gerhard Weikum",

year = "2013",

month = jan,

day = "1",

doi = "10.1016/j.artint.2012.06.001",

language = "English",

volume = "194",

pages = "28--61",

journal = "Artificial Intelligence",

issn = "0004-3702",

}

TY - JOUR

T1 - YAGO2

T2 - A spatially and temporally enhanced knowledge base from Wikipedia

AU - Hoffart, Johannes

AU - Suchanek, Fabian M.

AU - Berberich, Klaus

AU - Weikum, Gerhard

PY - 2013/1/1

Y1 - 2013/1/1

N2 - 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.

AB - 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.

KW - Information extraction

KW - Knowledge bases

KW - Ontologies

KW - Spatio-temporal facts

U2 - 10.1016/j.artint.2012.06.001

DO - 10.1016/j.artint.2012.06.001

M3 - Article

AN - SCOPUS:84870293219

SN - 0004-3702

VL - 194

SP - 28

EP - 61

JO - Artificial Intelligence

JF - Artificial Intelligence

ER -

YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia

Abstract

Keywords

Access to Document

Fingerprint

Cite this