/* ---- Google Analytics Code Below */

Sunday, October 28, 2018

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  .... " 

No comments: