TY - JOUR
T1 - Teaching machines about everyday life
AU - Singh, Push
AU - Barry, Barbara
AU - Liu, Hugo
N1 - Funding Information:
We would like to extend our thanks to all the people who have been involved with the Media Lab commonsense efforts since the beginning, and especially, to the many thousands of people who have contributed their knowledge to our databases. This work is supported by the sponsors of the MIT Media Lab.
PY - 2004/10
Y1 - 2004/10
N2 - In order to build software that can deeply understand people and our problems, we require computational tools that give machines the capacity to learn and reason about everyday life. We describe three commonsense knowledge bases that take unconventional approaches to representing, acquiring, and reasoning with large quantities of commonsense knowledge. Each adopts a different approach - ConcepNet is a large-scale semantic network, LifeNet is a probabilistic graphical model, and StotyNet is a database of stoty-scripts. We describe the evolution, architecture and operation of these three systems, and conclude with a discussion of how we might combine them into an integrated commonsense reasoning system.
AB - In order to build software that can deeply understand people and our problems, we require computational tools that give machines the capacity to learn and reason about everyday life. We describe three commonsense knowledge bases that take unconventional approaches to representing, acquiring, and reasoning with large quantities of commonsense knowledge. Each adopts a different approach - ConcepNet is a large-scale semantic network, LifeNet is a probabilistic graphical model, and StotyNet is a database of stoty-scripts. We describe the evolution, architecture and operation of these three systems, and conclude with a discussion of how we might combine them into an integrated commonsense reasoning system.
UR - http://www.scopus.com/inward/record.url?scp=8644220659&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=8644220659&partnerID=8YFLogxK
U2 - 10.1023/B:BTTJ.0000047601.53388.74
DO - 10.1023/B:BTTJ.0000047601.53388.74
M3 - Article
AN - SCOPUS:8644220659
SN - 1358-3948
VL - 22
SP - 227
EP - 240
JO - BT Technology Journal
JF - BT Technology Journal
IS - 4
ER -