A new method of ontology alignment is presented for knowledge graphs, called reciprocal mapping. The idea is to enhance a target knowledge base (in this case, KBpedia) with local graph structure and content from an external source knowledge base (in this case, Wikipedia) in order to fill gaps in the source. Show More Summary
This article deals with browsing the KBpedia knowledge structure, found under the Knowledge Graph main menu link on the Cognonto Web site. The article is a first in a new series covering non-machine learning use cases, already covered elsewhere, of the KBpedia knowledge graph.
Automatic Mappings of Tables to Knowledge Graphs and Open Table Extraction On the upcoming colloquium on 23.01.2017, Ivan Ermilov will present his work on automatic mappings of tables to knowledge graphs, which was published as TAIPAN:...Show More Summary
When Google launched its Knowledge Graph back in 2012, it was hailed by users and marketers alike as a breakthrough in search. Instead of sifting through page after page of results, you could instead get the detailed information you needed – and by extension, everything else you might want to know about the topic – […]
Posted by Jason Douglas, PM Director for Actions on Google The Google Assistant brings ogether all of the technology and smarts we've been building for years, from the Knowledge Graph to Natural Language Processing. To be a truly successful Assistant, it should be able to connect users across the apps and services in their lives. Show More Summary
Recent Slideshow Posted on KBpedia Last week I gave a presentation to the Ontolog Forum on Cognonto, with specific reference to the KBpedia knowledge structure. I am pleased to now post this presentation online: Context, Perspective, and Generalities in a Knowledge Ontology from Mike Bergman As a standard method, the Forum routinely records the audio […]
Google's knowledge graph card tests a feature that lets you like or dislike movies and TV shows. For example, when you search for "It's a Wonderful Life", you can click like or dislike and check the percentage of Google users who liked it. Show More Summary
The upper ontology for the KBpedia knowledge graph, the KBpedia Knowledge Ontology (KKO), has been updated to better capture the terminology of Charles Sanders Peirce and his universal categories to capture predicates (relations and attributes).
The U.S. Department of Veterans Affairs (VA) has signed a five-year deal with San Francisco, CA-based Flow Health to build a medical knowledge graph with deep learning to inform medical decision-making and train artificial intelligence (AI) to personalize care plans. Flow Health is building the world’s largest knowledge graph of medicine and genomics from over... Read More
Tweet Dissertation Proposal Dealing with Dubious Facts in Knowledge Graphs Ankur Padia 1:00-3:00pm Wednesday, 30 November 2016, ITE 325b, UMBC Knowledge graphs are structured representations of facts where nodes are real-world entities or events and edges are the associations among the pair of entities. Show More Summary
Cognonto today published two new use cases, bringing to six the lab notebook examples of how Cognonto technology and its KBpedia knowledge structure and knowledge graph may be employed.
In the first part of this series we found the good hyperparameters for a single linear SVM classifier. In part 2, we will try another technique to improve the performance of the system: ensemble learning. So far, we already reached 95%...Show More Summary
In my previous blog post, Create a Domain Text Classifier Using Cognonto, I explained how one can use the KBpedia Knowledge Graph to automatically create positive and negative training corpuses for different machine learning tasks. I...Show More Summary
The Cognonto demo is powered by an extensive knowledge graph called the KBpedia Knowledge Graph, as organized according to the KBpedia Knowledge Ontology (KKO). KBpedia is used for all kinds of tasks, some of which are demonstrated by the Cognonto use cases. Show More Summary
Microsoft has opened up a knowledge base of words linked to concepts to help machines get better at understanding human communications.
Today, Microsoft Research is publicly releasing its effort to tackle just one of the problems plaguing natural language understanding — knowledge. The company believes that background knowledge is one of the key separators between the way humans and machines understand language. Show More Summary
Cognonto's KBpedia knowledge graph can now be searched for both hundreds of thousands of concepts and 20 million entities.