Digital Intuition: Applying Common Sense Using Dimensionality Reduction

Understanding the world we live in requires access to a large amount of background knowledge: the commonsense knowledge that most people have and most computer systems don't. Many of the limitations of artificial intelligence today relate to the problem of acquiring and understanding common sen...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE intelligent systems 2009-07, Vol.24 (4), p.24-35
Main Authors:	Havasi, Catherine, Speer, Robyn, Pustejovsky, James, Lieberman, Henry
Format:	Article
Language:	eng
Subjects:	analogies Artificial intelligence Blending Computer science Digital Expert systems Intelligent systems Interactive computer systems Internet Knowledge acquisition knowledge base management LAN interconnection Large-scale systems Matrix representation natural language processing Natural languages Pattern analysis Representations Search engines semantic networks Semantics Technological change
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Understanding the world we live in requires access to a large amount of background knowledge: the commonsense knowledge that most people have and most computer systems don't. Many of the limitations of artificial intelligence today relate to the problem of acquiring and understanding common sense. The Open Mind Common Sense project began to collect common sense from volunteers on the Internet starting in 2000. The collected information is converted to a semantic network called ConceptNet. Reducing the dimensionality of ConceptNet's graph structure gives a matrix representation called AnalogySpace, which reveals large-scale patterns in the data, smoothes over noise, and predicts new knowledge. Extending this work, we have created a method that uses singular value decomposition to aid in the integration of systems or representations. This technique, called blending, can be harnessed to find and exploit correlations between different resources, enabling commonsense reasoning over a broader domain.
ISSN:	1541-1672 1941-1294