YAGO (database)

{{Short description|Open-source information repository}}

{{Infobox software

|name = YAGO

|logo = YAGO.svg

|screenshot =

|developer = Max-Planck-Institute Saarbrücken

|released = 2008

|latest_release_version = 4.5

|latest_release_date = May 2023{{cite web|url=https://yago-knowledge.org/|title=Home: Yago Project}}

|genre = Semantic Web, linked data

|license = Creative Commons CC-BY 4.0{{cite web|url=https://github.com/yago-naga/yago-4.5?tab=License-1-ov-file#readme|access-date=2024-10-31|title=License of YAGO4.5|website=GitHub }}

|website = {{URL|https://yago-knowledge.org/}}

}}

YAGO (Yet Another Great Ontology) is an open source{{Citation|title=yago3: YAGO is a large semantic knowledge base, derived from Wikipedia, WordNet, WikiData, GeoNames, and other data sources|date=2017-08-31|url=https://github.com/yago-naga/yago3|publisher=yago-naga|access-date=2017-08-31}} knowledge base developed at the Max Planck Institute for Informatics in Saarbrücken. It is automatically extracted from Wikidata and Schema.org.

YAGO4, which was released in 2020, combines data that was extracted from Wikidata with relationship designators from Schema.org.{{Cite web |date=24 June 2020 |title=The latest version of leading knowledge database, Yago |url=https://www.telecom-paris.fr/latest-version-leading-knowledge-database-yago |access-date=2024-06-12 |website=www.telecom-paris.fr |language=en}} The previous version of YAGO, YAGO3, had knowledge of more than 10 million entities and contained more than 120 million facts about these entities.{{cite web|url=http://www.mpi-inf.mpg.de/departments/databases-and-information-systems/research/yago-naga/yago/|access-date=2019-01-09|title=Yago}} The information in YAGO3 was extracted from Wikipedia (e.g., categories, redirects, infoboxes), WordNet (e.g., synsets, hyponymy), and GeoNames.Fabian M. Suchanek, Gjergji Kasneci and Gerhard Weikum.

"Yago – A Core of Semantic Knowledge".

16th international World Wide Web conference (WWW 2007) [http://suchanek.name/work/publications/www2007.pdf]

The accuracy of YAGO was manually evaluated to be above 95% on a sample of facts.{{cite web|url=http://www.mpi-inf.mpg.de/departments/databases-and-information-systems/research/yago-naga/yago/statistics/|access-date=2015-01-24|title=Yago Statistics}} To integrate it to the linked data cloud, YAGO has been linked to the DBpedia ontology{{cite web|url=http://www.mpi-inf.mpg.de/departments/databases-and-information-systems/research/yago-naga/yago/linking/|access-date=2015-01-24|title=Yago Linking}} and to the SUMO ontology.{{cite web|url=http://www.mpi-inf.mpg.de/~gdemelo/yagosumo/|access-date=2012-12-21|title=YAGO-SUMO}}

YAGO3 is provided in Turtle and tsv formats. Dumps of the whole database are available, as well as thematic and specialized dumps. It can also be queried through various online browsers and through a SPARQL endpoint hosted by OpenLink Software. The source code of YAGO3 is available on GitHub.

YAGO has been used in the Watson artificial intelligence system.David Ferrucci, Eric Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya A. Kalyanpur, Adam Lally, J. William Murdock, Eric Nyberg, John Prager, Nico Schlaefer, Chris Welty. Building Watson: An Overview of the DeepQA Project. AI Magazine 31(3): 59–79 (2010)