Commonsense Reasoning Task

From GM-RKB
(Redirected from Commonsense Reasoning)
Jump to navigation Jump to search

A Commonsense Reasoning Task is a reasoning task that involves common sense knowledges.



References

2023

  • (Wikipedia, 2023) ⇒ https://en.wikipedia.org/wiki/commonsense_reasoning Retrieved:2023-2-15.
    • In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. These assumptions include judgments about the nature of physical objects, taxonomic properties, and peoples' intentions. A device that exhibits commonsense reasoning might be capable of drawing conclusions that are similar to humans' folk psychology (humans' innate ability to reason about people's behavior and intentions) and naive physics (humans' natural understanding of the physical world).[1]
  1. Ernest Davis; Gary Marcus (2015). "Commonsense Reasoning and Commonsense Knowledge in Artificial Intelligence". Communications of the ACM. Vol. 58, no. 9. pp. 92–103. doi:10.1145/2701413.

2022

  • chat
    • Commonsense reasoning refers to the ability to make inferences and draw conclusions based on general knowledge and understanding of the world that is typically shared by most people. This type of reasoning is not based on formal logic or explicit rules, but rather on the implicit assumptions and associations that people make based on their experiences and observations.

      Commonsense reasoning involves making assumptions about cause and effect, understanding social norms and expectations, and predicting likely outcomes of everyday situations. It is the kind of reasoning that allows us to navigate the world and make decisions in a way that is consistent with our beliefs and values.

      Examples of commonsense reasoning might include understanding that if it's raining outside, you will get wet if you go outside without an umbrella, or that if you forget to set your alarm clock, you will oversleep and be late for work. These kinds of inferences are based on a wide range of implicit knowledge about the world, including knowledge about the laws of physics, social norms, and common human behavior.

      In artificial intelligence, commonsense reasoning is an area of research focused on developing algorithms and models that can simulate the kind of reasoning that humans use in everyday life. This is an important area of research because it has the potential to improve the ability of machines to understand and interact with the world in a more natural and intuitive way.

2015

  • (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Commonsense_reasoning Retrieved:2015-7-26.
    • Commonsense reasoning is the branch of Artificial intelligence concerned with simulating the human ability to make deductions about the kind of ordinary situations they encounter every day. This includes judgements about the physical properties, purpose, intentions and possible behavior of all ordinary things, such as people, cups, water, blocks, clouds, animals, and so on. A machine which exhibits commonsense reasoning will be capable of drawing conclusions that are similar to human's folk psychology (the innate human ability to reason about other people's intentions and mental states) or naive physics (the understanding of the physical world which every normal human child exhibits).

      There are several components to this problem, including:

      • Developing adequately broad and deep commonsense knowledge bases.
      • Developing reasoning methods that exhibit the features of human thinking, including the ability to:
        • reason with knowledge that is true by default
        • reason rapidly across a broad range of domains
        • tolerate uncertainty in your knowledge
        • take decisions under incomplete knowledge and perhaps revise that belief or decision when complete knowledge becomes available.
      • Developing new kinds of cognitive architectures that support multiple reasoning methods and representations.

1988