Posted:December 1, 2016

CognontoPublic Ontolog Forum Talk to Emphasize KBpedia

The Ontolog Forum, the online community of practice for ontologists, has just announced a public online meeting on Cognonto. I will be giving the roughly 60 min presentation, to be followed by 30 min of open discussion, on December 7 at 9:30am Pacific / 12:30pm Eastern / 6:30pm CEST / 5:30pm GMT / 1730 UTC.  The public is invited.

According to the announcement:

KBpedia is a recently announced knowledge structure that integrates six major knowledge bases (OpenCyc, Wikipedia, Wikidata, GeoNames, DBpedia, UMBEL) under the KBpedia Knowledge Ontology (KKO). KBpedia’s explicit purpose is to provide a foundation for knowledge-based artificial intelligence by supporting the (nearly) automatic creation of training corpuses and positive and negative training sets and feature sets for deep, unsupervised and supervised machine learning. KKO is the upper ontology for KBpedia, and is guided by the universal categories (Firstness, Secondness, Thirdness) of Charles S. Peirce. [This talk] will discuss what KBpedia is, how it is organized and constructed, and why KKO offers some new approaches to vexing metaphysical questions in ontology design related to the knowledge representation of entities, relations, attributes, concepts, and natural kinds. The discussion period will hopefully highlight next potentials and important open questions.

Instructions and dial-in numbers are provided on the meeting announcement site. Please note that Ontolog has an open intellectual property rights policy.

I hope to see you there!

Posted:November 28, 2016

Dataversity has just published an article on Cognonto based on an interview of me and review of our online materials. The article, Cognonto Takes On Knowledge-Based Artificial Intelligence,” does an excellent job of summarizing the venture. The writer, Jennifer Zaino, did a fantastic job capturing our discussions and framing the Cognonto story. Thanks!

I especially like that the article begins with the simple words, knowledge-based artificial intelligence, which is the quintessential description of what Cognonto is about. Jennifer then goes on to explain the genesis of the venture, the central role of its knowledge structure KBpedia, and the basis of this knowledge graph grounded in the triadic logic of the 19th century philosopher, Charles Sanders Peirce.

We will use this article for months to come in helping others understand what we are doing and why. It is always refreshing to see intelligent, well-written journalism. Thanks, Jenny.

Posted:November 22, 2016

CognontoSix Diverse Use Cases Now Available

Cognonto today published two new use cases on how to further leverage KBpedia, its knowledge structure that integrates six major knowledge bases (Wikipedia, Wikidata, OpenCyc, GeoNames, DBpedia and UMBEL), plus mappings to another 20 leading knowledge vocabularies. KBpedia provides a foundation for knowledge-based artificial intelligence (KBAI) by supporting the (nearly) automatic creation of training corpuses and positive and negative training sets and feature sets for deep, unsupervised and supervised machine learning.

The two new use cases are in: 1) dynamic tests and refinements of machine learners enabled by KBpedia’s fast creation of training sets and corpuses and reference (‘gold’) standards; and 2) KBpedia’s unique aspects that provide context for various entity types. With these two additions, Cognonto has now published six diverse use cases:

Each use case is summarized according to the problem and our approach to solving it and the benefits that result. The use cases themselves present general workflows and code snippets for how the use case was tackled.

We will continue to publish use cases using Cognonto’s technologies and KBpedia as they arise.

 

Posted:November 17, 2016

AI3 PulseInvited Article Provides Good KBAI Summary

I am pleased to point to a new invited article, “Wrestling Knowledge into Computable Intelligence,” published today on ODBMS.org. My article provides a high-level summary of recent trends in knowledge-based artificial intelligence and the mindsets and designs necessary to move KBAI forward. I think the article provides a pretty good summary (if I say so myself!) of the approach we take at Cognonto.

I’d like to thank Roberto Zicari for the invite to write in a style and brevity not typical of my normal articles. 😉  Enjoy!

Posted:November 15, 2016

CognontoUpper Structure, Typologies Updated

Cognonto today released version 1.10 of its KBpedia knowledge structure. KBpedia integrates six major knowledge bases (Wikipedia, Wikidata, OpenCyc, GeoNames, DBpedia and UMBEL), plus mappings to another 20 leading knowledge vocabularies, under the KBpedia Knowledge Ontology (KKO). KBpedia’s explicit purpose is to provide a foundation for knowledge-based artificial intelligence (KBAI) by supporting the (nearly) automatic creation of training corpuses and positive and negative training sets and feature sets for deep, unsupervised and supervised machine learning.

This new release focused on two major updates. First, certain aspects of the upper structure of the KKO were streamlined. And, second, KBpedia’s core typologies, which capture the overwhelming majority of reference concepts that are classified as entity types, were further organized to create tighter taxonomic structures.

The upper portion of the KBpedia knowledge graph required cleanup because it was still using some of the abstract-tangible distinctions used in Cyc. These distinctions were no longer used with the adoption of the universal categories of Charles S. Peirce (see my earlier article for more on this architectural design). This cleanup resulted in removing nearly 25% of the upper level links from the prior version (which were superfluous to the disjoint design of KBpedia). The typology organizations are part of an ongoing effort to streamline and tighten these structures.

Last week Cognonto’s CTO, Fred Giasson, described the general build processes we have in place for KBpedia. This release is another example of that process in action.

KBpedia contains nearly 40,000 reference concepts (RCs) and about 20 million entities. The combination of these and KBpedia’s structure results in over 6 billion logical connections across the system, as these KBpedia statistics show:

Measure Value
No KBpedia reference concepts (RCs) 39,052
No. mapped vocabularies 27
Core knowledge bases 6
Extended vocabularies 21
No. mapped classes 138,987
Core knowledge bases 137,322
Extended vocabularies 1,665
No. typologies (SuperTypes) 63
Core entity types 33
Other core types 5
Extended 25
Typology assignments 372,967
No. of “triples” in KBpedia ontology 1,347,818
No. aspects 80
Direct entity assignments 68,026,551
Inferred entity aspects 204,704,905
No. unique entities 19,643,718
Inferred no of entity mappings 2,541,684,526
Total no. of “triples” 3,689,849,183
Total no. of inferred and direct assertions 6,251,177,427
KBpedia v. 1.10 Statistics

This release of KBpedia is part of an ongoing series of releases to improve and extend the knowledge structure, as well as to increase its mappings to still additional external vocabularies. You can inspect the upper portions of the KBpedia knowledge graph on the Cognonto Web site. Also, if you have an ontology editor, you can download and inspect the open source KKO directly.

About Cognonto

The insight behind Cognonto is that existing knowledge bases can be staged to automate much of the tedium and reduce the costs now required to set up and train machine learners for knowledge purposes. Cognonto’s mission is to make knowledge-based artificial intelligence (KBAI) cheaper, repeatable, and applicable to enterprise needs.

Cognonto (a portmanteau of ‘cognition’ and ‘ontology’) exploits large-scale knowledge bases and semantic technologies for machine learning, data interoperability and mapping, and fact and entity extraction and tagging. Cognonto puts its insight into practice through a knowledge structure, KBpedia, designed to support AI, and a management framework, the Cognonto Platform, for integrating enterprise and external data to gain the advantage of KBpedia’s structure.

Cognonto automates away much of the tedium and reduces costs in many areas. Cognonto offers a number of use cases for how the Cognonto Platform and KBpedia in combination with enterprise information assets may be applied.