News

 

Open-source Baseline for KBpedia Now Available

02/04/2019

 

CORALVILLE, IA (02/04/2019) -- Cognonto Corporation today released version 2.00 of KBpedia, what the company is calling its first complete, open-source baseline of this knowledge artifact. This updated version nearly completes the mapping and coverage to Wikidata and Wikipedia, and completes definitions for all 55,000 reference concepts in KBpedia. Many other improvements and cleaning have been made to the general structure as well, due to detailed comparison of original source mappings.

Michael Bergman, the lead editor for KBpedia, noted that though KBpedia was first released as open source in October 2018 with version 1.60, this version represents what he and Fred Giasson, KBpedia's other editor, consider to be the true baseline release. "We needed to release it then [Oct 2018] because of the pending release of my new book, A Knowledge Representation Practionary: Guidelines Based on Charles Sanders Peirce, which has liberal ties to KBpedia," said Bergman. "We were pleased with that first open-source release, but did not have time to complete our full list of what we considered to be a proper baseline for KBpedia's initial release; we're pleased to have now completed that list," he added.

KBpedia is a computable knowledge graph that sits astride Wikipedia and Wikidata and other leading knowledge bases. Its baseline 55,000 reference concepts provide a flexible and expandable means for relating an enterprise's own data records to a common basis for reasoning and inferring logical relations and for mapping to virtually any external data source or schema. The framework is a clean starting basis for doing knowledge-based artificial intelligence (KBAI) and to train and use virtual agents.

KBpedia combines seven major public knowledge bases — Wikipedia, Wikidata, schema.org, DBpedia, GeoNames, OpenCyc, and UMBEL. KBpedia supplements these core KBs with mappings to more than a score of additional leading vocabularies. The entire KBpedia structure is computable, meaning it can be reasoned over and logically sliced-and-diced to produce training sets and reference standards for machine learning and data interoperability. KBpedia provides a coherent overlay for retrieving and organizing Wikipedia or Wikidata content. According to Cognonto, KBpedia's lead sponsor, the knowledge graph greatly reduces the time and effort traditionally required for knowledge-based artificial intelligence (KBAI) tasks.

KBpedia is also a comprehensive knowledge structure for promoting data interoperability. KBpedia's upper structure, the KBpedia Knowledge Ontology (KKO), is based on the universal categories and knowledge representation theories of the great 19th century American logician, philosopher, polymath and scientist, Charles Sanders Peirce. This design provides a logical and coherent underpinning to the entire KBpedia structure. The design is also modular and fairly straightforward to adapt to enterprise or domain purposes. Bergman's recently released book relates Peirce's insights to the design and use of KBpedia. One major aspect of Peirce's pragmatism is reflected by how KBpedia, and extensions specific to a given enterprise, may be deployed incrementally as benefits are gained each step of the way.

To complete this open-source baseline a number of areas received major attention:

• Definitions were completed for 100% of the 55,000 reference concepts;
• Mappings to instances and classes in Wikidata were greatly expanded to 32 million entities, representing over 80% of the useful data in that system;
• Mappings to Wikipedia represent similar coverage; and
  
• Significant clean up and removal of duplicates that resulted from combining KBpedia's constituent knowledge bases.

However, this release does not represent a major change in scope or size of KBpedia since cleanup removals were roughly balanced with the addition of new intermediate concepts to better tie together the overall knowledge graph.

The KBpedia Web site provides a working KBpedia explorer and demo of how the system may be applied to local content for tagging or analysis. KBpedia splits between entities and concepts, on the one hand, and splits in predicates based on attributes, external relations, and pointers or indexes, all informed by Charles Peirce's prescient theories of knowledge representation. Mappings to all external sources are provided in the linkages to the external resources file in the KBpedia downloads. (A larger inferred version is also available.) The external sources keep their own record files. KBpedia distributions provide the links. However, you can access these entities through the KBpedia explorer on the project's Web site (see these entity examples for cameras, cakes, and canyons; clicking on any of the individual entity links will bring up the full instance record. Such reachthroughs are straightforward to construct.) See further the Github site for further downloads. All resources are available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. KBpedia's development to date has been sponsored by Cognonto Corporation.

About KBpedia

The KBpedia knowledge structure combines seven (7) public knowledge bases - Wikipedia, Wikidata, schema.org, DBpedia, GeoNames, OpenCyc, and UMBEL - into an integrated whole. These core KBs are supplemented with mappings to more than a score of additional leading vocabularies. The entire KBpedia structure is computable, meaning it can be reasoned over and logically sliced-and-diced to produce training sets and reference standards for machine learning and data interoperability. KBpedia provides a coherent overlay for retrieving and organizing Wikipedia or Wikidata content. KBpedia greatly reduces the time and effort traditionally required for knowledge-based artificial intelligence (KBAI) tasks. KBpedia was first released in October 2016 with some open source aspects, with remaining restrictions now removed. KBpedia is sponsored by Cognonto Corporation.

Press Contact