ConceptNet aims to give computers access to common-sense knowledge, the kind of information that ordinary people know but usually leave unstated.
The data in ConceptNet is being collected from ordinary people who contributed it on sites like Open Mind Common Sense. ConceptNet represents this data in the form of a semantic network, and makes it available to be used in natural language processing and intelligent user interfaces.
ConceptNet is an open source project, with a Python implementation and a REST API that anyone can use to add computational common sense to their own project. A great tool to help you use ConceptNet in your software is Divisi.
Places to go next
ConceptNet Development Team
- Robert Speer, MIT
- Kenneth Arnold, MIT Media Lab Software Agents Group
- Catherine Havasi, MIT Media Lab
Papers about ConceptNet itself
Havasi, C., Speer, R. & Alonso, J. (2007) ConceptNet 3: a Flexible, Multilingual Semantic Network for Common Sense Knowledge. Proceedings of Recent Advances in Natural Languges Processing 2007. (paper)
Liu, H. & Singh, P. (2004) ConceptNet: A Practical Commonsense Reasoning Toolkit. BT Technology Journal, Volume 22. Kluwer Academic Publishers. (paper)
Liu, H. & Singh, P. (2004). Commonsense Reasoning in and over Natural Language Proceedings of the 8th International Conference on Knowledge-Based Intelligent Information & Engineering Systems (KES'2004). Wellington, New Zealand. September 22-24. Lecture Notes in Artificial Intelligence, Springer 2004 (paper)
We also use ConceptNet for a lot of other work; see the CSC papers list for a full list.