In artificial intelligence research, commonsense knowledge consists of facts about the everyday world, such as “Lemons are sour”, that all humans are expected to know. The first AI program to address common sense knowledge was Advice Taker in 1959 by John McCarthy .
It is currently an unsolved problem in Artificial General Intelligence and is a focus of the Paul Allen Institute for Artificial Intelligence. Commonsense knowledge can underpin a commonsense reasoning process, to attempt inferences such as “You might bake a cake because you want 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. Common sense knowledge also helps to solve problems in the face of incomplete information. Using widely held beliefs about everyday objects, or common sense knowledge, AI systems make common sense assumptions or default assumptions about the unknown similar to the way people do. In an AI system or in english, this is expressed as ‘Normally P holds’, ‘Usually P’ or ‘Typically P so Assume P’. For example if we know the fact ‘tweety is a bird’ , because we know the commonly held belief about birds, Typically Birds Fly, without knowing anything else about tweety, we may reasonably assume the fact that ‘tweety can fly.’ As more knowledge of the world is discovered or learned over time, the AI system can revise its assumptions about tweety using a truth maintenance process. If we later learn that ‘tweety is a penguin’ then truth maintenance revises this assumption because we also know ‘penguins do not fly’.
Commonsense reasoning simulates the human ability to make presumptions about the type and essence of ordinary situations they encounter every day, including time, missing or incomplete information and cause and effect. The ability to explain cause and effect is an important aspect of explainable AI. Compared with humans, all existing computer programs that attempt human-level AI 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), although some oppose this notion and believe compassionate intelligence is also required for human-level AI. Common sense reasoning has been applied successfully in more limited domains such as automated diagnosis or analysis.
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.
ConceptNet has also been used by chatbots and by computers that compose original fiction. At Lawrence Livermore National Laboratory, common sense knowledge was used in an intelligent software agent to detect violations of a comprehensive nuclear test ban treaty.
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
The common sense knowledge base is a knowledge base of contemporary intelligent systems or intelligent agents. It is a key measure to solve the bottleneck problem of artificial intelligence or knowledge engineering technology, which is characterized by a large scale. The domain knowledge base of early artificial intelligence or knowledge engineering systems is another kind of knowledge base. That is to say, the domain knowledge base and the common sense knowledge base are two basic types of knowledge bases possessed by intelligent computer systems. The field of computer science generally believes that the domain knowledge base and the common sense knowledge base are bottlenecks in artificial intelligence or knowledge engineering technology. From the early attention to the domain knowledge of experts to the current knowledge of common sense, this is an advancement in artificial intelligence or knowledge engineering technology. Due to the continuous maturity of computer hardware and software, as well as databases and data warehouses and their human-computer interaction interfaces, the large-scale domain knowledge bases and common knowledge systems required for the development of various expert systems in the 21st century are required. The common sense knowledge base of scale has basic conditions.
Common sense knowledge
In the study of artificial intelligence, common-sense knowledge is the facts collected and information that a common person foresees. The common-sense knowledge problem is an ongoing project that belongs to the field of knowledge expression (a branch of artificial intelligence). It aims to create a common sense knowledge base: a database containing all the general knowledge that most people have. It is expressed in a way that makes it possible to use natural language in artificial intelligence programs or to make inferences about the ordinary world. Such a database is an ontology of knowledge, the most common of which is the so-called upper ontology.
issues that need resolving
The problem of multi-threaded work is considered to be the most difficult, because the breadth of knowledge and detailed common-sense knowledge of artificial intelligence research is enormous. Any task that requires common-sense knowledge is considered to be done by artificial intelligence: a lot of work to do, and what one does not have, it requires the machine to show its intelligence as a person. These tasks include machine translation, object recognition, text mining, and many other issues. To perform these tasks perfectly, the machine simply knows what the text is talking about and the object is visible, which is impossible unless the machine is familiar with the same concepts that a common person is familiar with.
Common sense content list
Information in the common sense knowledge base may include, but is not limited to, the following:
Ontology class and individual
Part and material of the object
The properties of the object (such as color and size)
Object function and use
Object location and distribution
Action and event location
Time of action and event
Prerequisites for actions and events
Action and event impact (post-conditions)
Subject and object of action
Stale of the situation or script
Human rights goals and needs
Planning and strategy
WordNet, a dictionary of common sense knowledge base.
(Large) Common Knowledge Base (Cyc), a large-scale common sense knowledge base similar to an encyclopedia.
ThoughtTreasure, a knowledge base of common sense in natural language processing.
Semantic Web, It is a future network with both a domain knowledge base and a common sense knowledge base.
Open Mind Common Sense
Basic formal knowledge ontology (Basic Formal Ontology
General Formal Ontology
Concept Network (ConceptNet)
Thought dot matrix (Mindpixel)
Ontology (computer science)
Upper or upper knowledge ontology)
Some experts believe that “common knowledge processing is the core problem of artificial knowledge research.” Some experts believe that “how to effectively acquire the knowledge of domain experts has always been a problem in artificial intelligence.”
For example, the ontology structure and operational mechanism of a large-scale common sense knowledge base for intelligent agents are studied.
Open Mind Common Sense (data source) and ConceptNet (datastore and NLP engine)
Source from Wikipedia