Commonsense knowledge (artificial intelligence)
In artificial intelligence research, a commonsense knowledge base is a semantic network that focuses on capturing commonsense knowledge. Commonsense knowledge consists of facts about the everyday world, such as "Lemons are sour", that all humans are expected to know. Commonsense knowledge can underpin a commonsense reasoning process, to attempt inferences such as "You might bake a cake because you want to people to eat the cake". A natural language processing process can be attached to the commonsense knowledge base to allow the knowledge base to attempt to answer commonsense questions about the world.
Commonsense reasoning simulates the human ability to make presumptions about the type and essence of ordinary situations they encounter every day. Compared with humans, all existing computer programs perform extremely poorly on modern "commonsense reasoning" benchmark tests such as the Winograd Schema Challenge. The problem of attaining human-level competency at "commonsense knowledge" tasks is considered to probably be "AI complete" (that is, solving it would require the ability to synthesize a fully human-level intelligence).
Around 2013, MIT researchers developed BullySpace, an extension of the commonsense knowledgebase ConceptNet, to catch taunting social media comments. BullySpace included over 200 semantic assertions based around stereotypes, to help the system infer that comments like "Put on a wig and lipstick and be who you really are" are more likely to be an insult if directed at a boy than a girl.
As an example, as of 2012 ConceptNet includes these 21 language-independent relations:
- CreatedBy ("cake" can be creating by "baking")
- AtLocation (Somewhere a "cook" can be is a "restaurant")
- SymbolOf (X represents Y)
- ReceivesAction ("cake" can be "eaten")
- HasPrerequisite (X can't do Y unless A does B)
- MotivatedByGoal (You would "bake" because you want to "eat")
- CausesDesire ("baking" makes you want to "follow recipe")
- HasFirstSubevent (The first thing required when you're doing X is for entity Y to do Z)
- HasSubevent ("eat" has subevent "swallow")
Commonsense knowledge bases
- Open Mind Common Sense (data source) and ConceptNet (datastore and NLP engine)
- True Knowledge
- DBpedia
- Liu, Hugo, and Push Singh. "ConceptNet—a practical commonsense reasoning tool-kit." BT technology journal 22.4 (2004): 211-226.
- "The Winograd Schema Challenge". cs.nyu.edu. Retrieved 9 January 2018.
- Yampolskiy, Roman V. "AI-Complete, AI-Hard, or AI-Easy-Classification of Problems in AI." MAICS. 2012.
- Andrich, C, Novosel, L, and Hrnkas, B. (2009). Common Sense Knowledge. Information Search and Retrieval, 2009.
- Bazelon, Emily (March 2013). "How to Stop the Bullies". The Atlantic. Retrieved 9 January 2018.
- Dinakar, Karthik; Jones, Birago; Havasi, Catherine; Lieberman, Henry; Picard, Rosalind (1 September 2012). "Common Sense Reasoning for Detection, Prevention, and Mitigation of Cyberbullying". ACM Transactions on Interactive Intelligent Systems. 2 (3): 1–30. doi:10.1145/2362394.2362400.
- "AI systems could fight cyberbullying". New Scientist. 27 June 2012. Retrieved 9 January 2018.
- "'I Believe That It Will Become Perfectly Normal for People to Have Sex With Robots'". Newsweek. 23 October 2014. Retrieved 9 January 2018.
- "Told by a robot: Fiction by storytelling computers". New Scientist. 24 October 2014. Retrieved 9 January 2018.
- Speer, Robert, and Catherine Havasi. "Representing General Relational Knowledge in ConceptNet 5." LREC. 2012.