Systems & Languages


A Knowledge Graph-based Semantic Database for Biomedical Sciences

@machinelearnbot

In short: BioGrakn is a graph-based semantic database that takes advantage of the power of knowledge graphs and machine reasoning to solve problems in the domain of biomedical science. We address the major issue of semantic integrity, that is, interpreting the real meaning of data derived from multiple sources or manipulated by various tools. We've discussed how BioGrakn takes advantage of the power of knowledge graphs and machine reasoning to solve problems in the domain of biomedical science. We address the major issue of semantic integrity, that is, interpreting the real meaning of data derived from multiple sources or manipulated by various tools.


An anecdotic tour on the history of programming languages

#artificialintelligence

It was named C because it was an improved B, a previous programming language, which was a simplified BCPL (hence its name). A language for computers written in 1972 being a part of an ancient religion? Five years later, in 1987, Larry Wall started working on Perl and at the end of the year version 1.0 was ready. Unfortunately, Larry, like all programmers, was more interested in writing code than its documentation, so it took 4 years and the wide adoption of the language for the Camel Book, the classic Perl book, to be written.



LinkedIn Knowledge Graph Enriches Data Value - insideBIGDATA

#artificialintelligence

LinkedIn data represents the world's largest online professional network, with relationships among more than 467M members, 290M jobs and 9M organizations through professional entities and attributes. The LinkedIn Knowledge Graph standardizes entities and relationships by forming the ontology of the professional world on top of entity taxonomies, which define the identity and attributes of each entity and the relationships among the entities. To improve the quality of knowledge generation, all intra-entity relationships (e.g., parent-child relationships between organizations) and inter-entity relationships (e.g., a member has a certain skill, that certain skill is needed by a job) in the Knowledge Graph are computed by state-of-the-art artificial intelligence methods and, when necessary, verified by domain experts. For example, LinkedIn auto-generates a personalized profile summary based on professional entities inferred by the Knowledge Graph, and recommends it to members who don't have completely standardized profiles.


[1703.05614] ParaGraphE: A Library for Parallel Knowledge Graph Embedding

@machinelearnbot

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)


Graphical Models

AITopics Original Links

In particular, we essentially decouple all the nodes, and introduce a new parameter, called a variational parameter, for each node, and iteratively update these parameters so as to minimize the cross-entropy (KL distance) between the approximate and true probability distributions. A more efficient approach in high dimensions is called Monte Carlo Markov Chain (MCMC), and includes as special cases Gibbs sampling and the Metropolis-Hasting algorithm.


Spreading Activation Mobile app could stop suicide by analysing language to spot risk

Daily Mail

Called Spreading Activation Mobile, or SAM, the app (pictured) can be used to record a counselling session. In the study, researchers tested the algorithm on 379 patients who were suicidal, diagnosed as mentally ill, or neither. By analysing speech patterns and non-verbal cues - such as pauses and sighs in speech - it could correctly classify if someone is suicidal with 93 per cent accuracy. Called Spreading Activation Mobile, or SAM, the app can be used to record a counselling session.



Building and Maintaining the KBpedia Knowledge Graph

#artificialintelligence

The Cognonto demo is powered by an extensive knowledge graph called the KBpedia Knowledge Graph, as organized according to the KBpedia Knowledge Ontology (KKO). The KBpedia Knowledge Graph is a structure of more than 39,000 reference concepts linked to 6 major knowledge bases and 20 popular ontologies in use across the Web. It is for these reasons that we developed an extensive knowledge graph building process that includes a series of tests that are run every time that the knowledge graph get modified. The process of checking if external concepts linked to the KBpedia Knowledge Graph satisfies the structure is the same.


LinkedIn Knowledge Graph – KDnuggets Interview

#artificialintelligence

We interview LinkedIn about their recently published LinkedIn Knowledge Graph which connects their many millions of members, jobs, companies, and more.