Golden: An Intelligent Knowledge Base

Brought to my attention:  Golden, quite a considerable breadth of claims.

The intelligent knowledge base
Explore the world's first self-constructing knowledge database built by artificial and human intelligence.

Authoritative knowledge at your fingertips
Access a growing body of knowledge. Follow topics you're interested in. Explore new topics to create a personalized knowledge feed.

Query across the Golden Knowledge Base
The Golden Research Engine is a comprehensive knowledge tool to research and track information on specific topics including companies, investment funds, cryptocurrencies, crypto projects, people and more.

Request deep information on a topic
Click a button to trigger fast turnaround of full information surrounding a topic of interest. Trigger research requests on information around a query and our AI-enabled helpers will max out the data request.

Frictionless tools to compile knowledge
Golden is building an interface to compile and comprehend knowledge. Frictionless editing, enhanced fact validation systems, transparent version histories and topic tracking.

A new standard for evidence
Golden will compile deeper evidence to validate claims and verify knowledge. High-resolution citations and bibliometrics will allow users to determine the provenance of information and evaluate source credibility.

Human knowledge meets AI
Golden draws on the strengths of both humans and machines. Statistical models and heuristic algorithms will handle repetitive work and automate the process of gathering knowledge.  ... " 

Microsoft Project Cortex

Brought to my attention from this weeks Build meetings as about to be launched.   Form of knowledge management.  Had been show very early version of this.  Notion of a semantic Web has been around for a long time, though not used often enough.   Will be following this.

Project Cortex

Today, we’re pleased to introduce Project Cortex, the first new service in Microsoft 365 since the launch of Microsoft Teams. Project Cortex uses advanced AI to deliver insights and expertise in the apps you use every day, to harness collective knowledge and to empower people and teams to learn, upskill and innovate faster.

Project Cortex uses AI to reason over content across teams and systems, recognizing content types, extracting important information, and automatically organizing content into shared topics like projects, products, processes and customers. Cortex then creates a knowledge network based on relationships among topics, content, and people.

New topic pages and knowledge centers—created and updated by AI—enable experts to curate and share knowledge with wiki-like simplicity. And topic cards deliver knowledge just-in-time to people in Outlook, Microsoft Teams, and Office.  ... " 

Knowledge Base Construction

Ultimate its what AI is about. Developing and storing knowledge, updating it and applying it to skills in context.   We worked with Stanford on this, but it had not yet been developed enough.   Are we ready for its application?  Especially in an era where machine learning is key.   Still don't see this well enough implemented where knowledge can be readily shared and integrated with context, common sense or otherwise.

Research for Practice

Knowledge Base Construction in the Machine-learning Era
Three critical design points: Joint-learning, weak supervision, and new representations  By Alex Ratner and Chris Ré

This installment of Research for Practice features a curated selection from Alex Ratner and Chris Ré, who provide an overview of recent developments in Knowledge Base Construction (KBC). While knowledge bases have a long history dating to the expert systems of the 1970s, recent advances in machine learning have led to a knowledge base renaissance, with knowledge bases now powering major product functionality including Google Assistant, Amazon Alexa, Apple Siri, and Wolfram Alpha. Ratner and Ré's selections highlight key considerations in the modern KBC process, from interfaces that extract knowledge from domain experts to algorithms and representations that transfer knowledge across tasks. Please enjoy! —Peter Bailis

More information is accessible today than at any other time in human history. From a software perspective, however, the vast majority of this data is unusable, as it is locked away in unstructured formats such as text, PDFs, web pages, images, and other hard-to-parse formats. The goal of KBC (knowledge base construction) is to extract structured information automatically from this "dark data," so that it can be used in downstream applications for search, question-answering, link prediction, visualization, modeling and much more. Today, KBs (knowledge bases) are the central components of systems that help fight human trafficking,18 accelerate biomedical discovery,9 and, increasingly, power web-search and question-answering technologies.4  .... "