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...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/51870 |
| _version_ | 1826208380737290240 |
|---|---|
| author | Havasi, Catherine Pustejovsky, James Speer, Robert H. Lieberman, Henry A. |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Havasi, Catherine Pustejovsky, James Speer, Robert H. Lieberman, Henry A. |
| author_sort | Havasi, Catherine |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T14:04:52Z |
| format | Article |
| id | mit-1721.1/51870 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:04:52Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/518702022-09-28T18:14:03Z Digital Intuition: Applying Common Sense Using Dimensionality Reduction Havasi, Catherine Pustejovsky, James Speer, Robert H. Lieberman, Henry A. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Media Laboratory Lieberman, Henry A. Speer, Robert H. Lieberman, Henry A. 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. Bank of America Schlumberger Microsoft 2010-03-01T21:01:32Z 2010-03-01T21:01:32Z 2009-07 Article http://purl.org/eprint/type/JournalArticle 1541-1672 http://hdl.handle.net/1721.1/51870 Havasi, C. et al. “Digital Intuition: Applying Common Sense Using Dimensionality Reduction.” Intelligent Systems, IEEE 24.4 (2009): 24-35. © 2009 Institute of Electrical and Electronics Engineers en_US http://dx.doi.org/10.1109/MIS.2009.72 IEEE Intelligent Systems Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Havasi, Catherine Pustejovsky, James Speer, Robert H. Lieberman, Henry A. Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title | Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title_full | Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title_fullStr | Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title_full_unstemmed | Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title_short | Digital Intuition: Applying Common Sense Using Dimensionality Reduction |
| title_sort | digital intuition applying common sense using dimensionality reduction |
| url | http://hdl.handle.net/1721.1/51870 |
| work_keys_str_mv | AT havasicatherine digitalintuitionapplyingcommonsenseusingdimensionalityreduction AT pustejovskyjames digitalintuitionapplyingcommonsenseusingdimensionalityreduction AT speerroberth digitalintuitionapplyingcommonsenseusingdimensionalityreduction AT liebermanhenrya digitalintuitionapplyingcommonsenseusingdimensionalityreduction |