Release Constitutes What We Consider As First, Complete Open-Source Baseline

We first released KBpedia as open source in October 2018 with version 1.60. We needed to release it then because of the pending release of my new book, A Knowledge Representation Practionary: Guidelines Based on Charles Sanders Peirce (Springer), which has liberal ties to KBpedia. We were pleased with that first open-source release of KBpedia, but did not have time to complete our full list of what we considered to be a proper baseline for the initial release. We have spent the past few months completing that list and are now pleased to announce version 2.00 of KBpedia, what we consider to be the first complete, open-source baseline of this knowledge artifact.

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 your 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. KBpedia 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. KBpedia provides a powerful reference scaffolding for bringing together your own internal data stovepipes into a comprehensive whole. KBpedia, and extensions specific to your own domain needs, can be deployed incrementally, gaining benefits each step of the way, until you have a computable overlay tieing together all of your valuable information assets.

Major Activities to Complete the Baseline

Some areas received major attention and some were largely ignored in completing this open-source baseline of KBpedia. For example, no changes (other than minor cleanup often related to other changes) were made to the property scope of KBpedia or their mappings to Wikidata or schema.org. The typologies were also not adjusted or expanded (except for minor cleanup related to other changes). The general scope of KBpedia remained virtually unchanged. However, a number of areas were targeted for specific attention and improvement. Notably:

• Definitions were completed for 100% of the 55,000 reference concepts. Since the decision to open source KBpedia, the number of concepts with definitions grew by nearly 40%, or new definitions for about 15,000 entries;
• Mappings to instances and classes in Wikidata were greatly expanded. Mappings now exist to 32 million entities in Wikidata, representing over 80% of the useful data in that system [1].  Over 80% of KBpedia’s 55 K reference concepts are also now mapped to specific Wikidata entries;
• Mappings to Wikipedia also grew and kept pace with this Wikidata mapping. Total mappings to Wikipedia only grew 10% because of the larger number of prior mappings. Still, coverage of Wikipedia is also now about 80% based on either mapped RCs or coverage of Wikipedia articles;
• Due to early mapping choices, KBpedia was not consistent in the use of plural v singular terms. We inspected and converted about 4500 plural concepts into singular expressions, consistent with what we see as best naming practices;
• Because of this mixed naming, and some other synonym issues, we had a pool of reference concept (RC) duplicates in the system that totaled nearly 1400 items, which were consolidated and then removed. The overall size of KBpedia, however, did not change much, since all of these inspections also resulted in the addition of about 1200 new concepts, often at intermediate layers that improved the overall graph connectivity; and
• Since the initiation of KBpedia, about 21,000 new concepts have been added over the starting OpenCyc RC structure. Each of these 21,000 RCs was reviewed, with about 5,000 flagged for detailed scrutiny. All of these flagged items were further reviewed, frequently resulting in new definitions, new parental assignments, new altLabels, or the addition of other property relations.

Despite these massive efforts, we are certainly not claiming an error-free structure. Logic and consistency tests are a constant activity and the addition or deletion of new concepts also requires testing and sometimes changes. Nonetheless, we are proud of this version 2.00 and believe KBpedia to be the cleanest it has ever been.

Statistics on the KBpedia v 200 Release

I show in the following table the statistics and changes compared to the first open-source release of KBpedia (v. 160) and the prior and last proprietary release (v. 151). The comparison to v 151 represents the total changes in the move to open source. Please note in the table that we measure coverage as the either the larger of: a) percent of external concepts mapped; or b) percent of KBpedia RCs mapped to the external source (predominantly unique).

The table shows the significant improvements made to KBpedia since the decision to release it as open source. The property mappings nearly doubled, now with significant mappings to both Wikidata and schema.org properties. The amount of mappings to Wikidata entities (Q items) increased nearly eight-fold (8 x), with coverage now more than 80 percent to both Wikidata and Wikipedia. The structure is fairly clean and consistent, with all reference concepts now including a definition, and most with a slew of alternative labels to improve matching and retrieval. Through its mapped sources, KBpedia links to more than 30 million entities, most all with data attributes (Wikidata) and complete articles (Wikipedia). The system is inherently designed for expansion into multiple languages.

Moving Beyond the Baseline

Of course, a knowledge artifact like KBpedia can be bounded in many ways. It is somewhat arbitrary what we define as a proper baseline. Our general image was a clean and computable framework adhering to best practices that maps to at least 80% of both Wikipedia and Wikidata. We have accomplished this baseline in the current release.

But our ambitions for KBpedia do not end there. Here are some of the major areas we will be working on for future versions:

• Still better definitions for many concepts, particularly those with short or limited definitions. A few thousand candidates exist for this attention;
• Adding another 1,000 or so new Wikidata Q items will increase instance coverage to more than 97% and raise class coverage to over 80%;
• Complete the products and services mappings to the UNSPSC (United Nations Standard Products and Services Code) classification scheme, plus the likely split of the Products typology into three distinct branches;
• Improved automatic tests for errors and oversights. We will be documenting our mapping experiences, among other topics, in a new ‘In the Trenches’ blog series I will begin early this year;
• Test marginal overlaps between SuperTypes (typologies) for various reference concepts in order to improve assignments and increase disjointedness assertions even further;
• Cross-check existing mappings from external sources to Wikidata against KBpedia assignments (GeoNames features, for example) and reconcile differences;
• Create various vector files for the KBpedia reference nodes using techniques such as explicit semantic analysis (ESA), word2vec, GloVe, and perhaps others; and
• Open source the build code for KBpedia.

Quite a while back I estimated that KBpedia might eventually grow to 85 K reference concepts or so in order to provide an equivalent, complete baseline coverage of topics across human knowledge domains. After this most recent detailed review, I think those prior numbers to be an overestimate. After detailed inspection and comparison with Wikipedia and Wikidata, I now suspect a ‘complete’ structure may require only 60 K to 65 K reference concepts. (Of course, the depth or breadth of KBpedia are virtually expandable to capture any knowledge domain.) This reduced estimate also includes that the present KBpedia has perhaps 1000 – 2000 unduly specific items (lists of individual species, for example) that probably should be culled to bring the overall structure into balance.

In any case, we welcome suggestions for further enhancements or tackling your own improvements. Please let me know what ideas you may have.

To Get the Goodies

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.)

Here are the various KBpedia resources that you may download or use for free with attribution:

• The complete KBpedia v 200 knowledge graph (8.5 MB, zipped). This download is likely your most useful starting point
• KBpedia’s upper ontology, KKO (332 KB), which is easily inspected and navigated in an editor
• The annotated KKO (321 KB). This is NOT an active ontology, but is has the upper concepts annotated to more clearly show the Peircean categories of Firstness (1ns), Secondness (2ns), and Thirdness (3ns)
• The 68 individual KBpedia typologies in N3 format
• The KBpedia mappings to the seven core knowledge bases and the additional extended knowledge bases in N3 format
• A version of the full KBpedia knowledge graph extended with linkages to the external resources (10.5 MB, zipped), and
• A version of the full KBpedia knowledge graph extended with inferences and linkages (14.7 MB, zipped).

The last two resources require time and sufficient memory to load. We invite and welcome contributions or commentary on any of these resources.

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.

Notes

Better Mappings, More Properties

When we released KBpedia v 1.60 as open source a couple of weeks back, I noted that I would follow-up the announcement with more details on the changes made in preparation for the release. This post provides that update.

KBpedia is a computable knowledge structure that 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. KBpedia greatly reduces the time and effort traditionally required for knowledge-based artificial intelligence (KBAI) tasks.

KBpedia is a comprehensive knowledge structure for promoting data interoperability and KBAI. 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. KBpedia was first released in October 2016. My initial announcement provides further details on KBpedia and how to download it.

Besides prepping the KBpedia knowledge artifiact for open-source release, we also made these improvement to the base structure in comparison to the prior v 1.51, the last proprietary version:

• The major effort was to increase the mapping to Wikidata, with most mappings represented as owl:equivalentClass. Coverage of KBpedia to Wikidata is now 50%, with 27,423 of KBpedia’s reference concepts now mapped to Wikidata. Version 1.60 has 4.5x more coverage than the previous v. 1.51
• We also continued to increase coverage to Wikipedia, with coverage now at 77%
• We now have essentially complete coverage to DBpedia ontology, schema.org and GeoNames
• We doubled the number of mapped properties to nearly 5 K and added schema.org property mappings
• We organized the properties into attributes, indexes/indices, and external relations.

Please note we measure coverage as the larger of percent of external concepts mapped or percent of KBpedia mapped to the external source. The % Change figures represent the changes from v 1.51 to the new open source v 1.60.

Besides the property organization, we made few changes in this latest v 1.60 release to the overall structure or scope of KBpedia. The emphasis was on mapping to existing sources and clean up for public release. Here are the major statistics for v 1.60:

Through its mapped sources, KBpedia links to more than 30 million entities, the largest percentage coming from Wikidata. The mappings to these 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.)

Please know that KBpedia remains under active development, with new updates anticipated in the near future. We are incorporating feedback gained from the initial open source release, and are also committed to increasing the mapping coverage for the artifact and other baseline improvements. Our plan is to complete this baseline before new external sources are added to the system.

KBpedia is 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.

A Major Milestone in Semantic Technologies and AI After a Decade of Effort

Fred Giasson and I are very (no, make that supremely!) pleased to announce the availability of KBpedia as open source. Woohoo! The complete open source KBpedia includes its upper ontology (KKO), full knowledge graph, mappings to major leading knowledge bases, and 70 logical concept groupings called typologies. We are also today announcing version 1.60 of KBpedia, with greatly expanded mappings.

For those who have been following our work, it should be clear that this release represents the culmination of more than ten years of steady development. KBpedia is the second-generation knowledge graph successor to UMBEL, which we will now begin to retire. KBpedia, when first released in 2016, only provided its upper portion, the KBpedia Knowledge Ontology (KKO), as open source. While we had some proprietary needs in the first years of the structure, we’re really pleased to return to our roots in open source semantic technologies and software. Open source brings greater contributions and greater scrutiny, both important to growth and improvements.

KBpedia is a computable knowledge structure that 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. KBpedia greatly reduces the time and effort traditionally required for knowledge-based artificial intelligence (KBAI) tasks.

KBpedia is a comprehensive knowledge structure for promoting data interoperability and KBAI. KBpedia’s upper structure, KKO, is based on the universal categories and knowledge representation theories of the great 19th century American logician, polymath and scientist, Charles Sanders Peirce. This design provides a logical and coherent underpinning to the entire structure. The design is also modular and fairly straightforward to adapt to enterprise or domain purposes. KBpedia was first released in October 2016.

“We began KBpedia with machine learning and AI as the driving factors,” said Fred, also the technical lead on the project. “Those remain challenging, but we are also seeing huge demands to bring a workable structure that can leverage Wikidata and Wikipedia,” he said. “We are seeing the convergence of massive public data with open semantic technologies and the ideas of knowledge graphs to show the way,” he stated. Here are some of the leading purposes and use cases for KBpedia:

• • A coherent and computable overlay to both Wikipedia and Wikidata
  • Integrating domain data
  • Fine-grained entity identification, extraction and tagging
  • Faceted, semantic search and retrieval
  • Mapping and integration of external datasets
  • Natural language processing and computational linguistics
  • Knowledge graph creation, extension and maintenance
  • Tailored filtering, slicing-and-dicing, and extraction of domain knowledge structures
  • Data harvesting, transformation and ingest
  • Data interoperability, re-use of existing content and data assets, and knowledge discovery
  • Supervised, semi-supervised and distant supervised machine learning for:
    • Typing, classification, extraction, and tagging of entities, attributes and relations
  • Unsupervised and deep learning.

  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. I will have much further to say about the project and its relation to Peirce in the coming weeks.

  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. The system is inherently multi-lingual, though the current release is in English only. We hope to see multiple language versions emerge, which should be straightforward given the dominance of links from Wikipedia and Wikidata. As it stands, the core structure of KBpedia provides direct links to millions of external reference sources. A subsequent post will document the changes in version 1.60 in detail.

  With this open source release, we will next shift our attention to expand the coverage of links to external sources. By moving to open source, we hope to see problems with the structure emerge as well as contributions now come from others. When you pull back the curtain with open source a premium gets placed on having clean assignments and structure that can stand up to inspection. Fortunately, Fred has designed a build system that starts with clean ‘triples’ input files.We make changes, re-run the structure against logic and consistency tests, fix the issues, and run again. We conducted tens of builds of the complete KBpedia structure in the transition from the prior versions to the current release. While we have a top-down design based on Peirce, we build the entire structure from the bottom up from these simple input specifications. The next phase in the our KBpedia release plan is also to release these build routines as open source.

  Though tremendous strides have been made in the past decade in leveraging knowledge bases for artificial intelligence, we are butting up against two limitations. Our first problem is that we are relying on knowledge sources like Wikipedia that were never designed for AI or data integration purposes. The second problem is that we do not have repeatable building blocks that can be extended to any domain or any enterprise. AI is sexy and attractive, but way too expensive. We hope the current open source release of KBpedia moves us closer to overcoming these problems.

  Downloads

  Here are the various KBpedia resources that you may download or use with attribution:

  • The complete KBpedia knowledge graph (7 MB, zipped). This download is likely your most useful starting point
  • KBpedia’s upper ontology, KKO (304 KB), which is easily inspected and navigated in an editor
  • The annotated KKO (291 KB). This is NOT an active ontology, but is has the upper concepts annotated to more clearly show the Peircean categories of Firstness (1ns), Secondness (2ns), and Thirdness (3ns)
  • The 68 individual KBpedia typologies in N3 format
  • The KBpedia mappings to the seven core knowledge bases and the additional extended knowledge bases in N3 format
  • A version of the full KBpedia knowledge graph extended with linkages to the external resources (8.7 MB, zipped), and
  • A version of the full KBpedia knowledge graph extended with inferences and linkages (11.6 MB, zipped).

  The last two resources require time and sufficient memory to load. We invite and welcome contributions or commentary on any of these resources.

  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.