The Community for Technology Leaders
Green Image
Issue No. 04 - July/August (2009 vol. 24)
ISSN: 1541-1672
pp: 24-35
Henry Lieberman , Massachusetts Institute of Technology
Catherine Havasi , Massachusetts Institute of Technology
Robert Speer , Massachusetts Institute of Technology
James Pustejovsky , Brandeis University
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.
semantic networks, analogies, knowledge acquisition, natural language processing, knowledge base management
Henry Lieberman, Catherine Havasi, Robert Speer, James Pustejovsky, "Digital Intuition: Applying Common Sense Using Dimensionality Reduction", IEEE Intelligent Systems, vol. 24, no. , pp. 24-35, July/August 2009, doi:10.1109/MIS.2009.72
109 ms
(Ver 3.1 (10032016))