KBpedia, a computable knowledge structure that integrates seven leading public knowledge bases such as Wikipedia and Wikidata, has been released as open source. KBpedia may be used to build enterprise or domain knowledge graphs. In addition, it can be used for data integration, knowledge-based artificial intelligence, entity and relation recognition and extraction, and content classification, among a myriad of other uses. This open source release includes KBpedia's upper ontology, full knowledge graph, mappings to major leading knowledge bases, and 70 logical concept groupings called typologies.
The KBpedia website provides a working KBpedia explorer and a demo of how the system may be applied to local content for tagging or analysis. On one hand, KBpedia splits between entities and concepts. On the other hand, it splits in predicates based on attributes, external relations, and pointers or indexes.
The new v 1.60 release of KBpedia has 55,000 reference concepts in its guiding knowledge graph, which ties into an estimated 30 million entities, mostly from Wikidata. Though the current release is in English, the system is inherently multi-lingual. As it stands, the core structure of KBpedia provides direct links to millions of external reference sources. With this open source release, attention will now be focused on expanding the coverage of links to external sources.
Click here to read the article.
Please give your feedback on this article or share a similar story for publishing by clicking here.
