Commonsense reasoning and commonsense knowledge in artificial intelligence

  title={Commonsense reasoning and commonsense knowledge in artificial intelligence},
  author={Ernest Davis and Gary F. Marcus},
  journal={Communications of the ACM},
  pages={92 - 103}
AI has seen great advances of many kinds recently, but there is one critical area where progress has been extremely slow: ordinary commonsense. 

Figures and Tables from this paper

Logical Formalizations of Commonsense Reasoning: A Survey

  • E. Davis
  • Computer Science
    J. Artif. Intell. Res.
  • 2017
This paper surveys the use of logic-based representations of commonsense knowledge in artificial intelligence research and describes the current state of the art in this area.

Can Ai Be Intelligent?

An attempt to give an answer to the question what does it mean that a computational system is intelligent, based on some theses that though debatable are commonly accepted.

Analysing the Practicality of Drawing Inferences in Automation of Commonsense Reasoning

A detailed analysis of representation of reasoning uncertainties and feasible prospects of existing inference methods for reasoning is presented and the possible impacts of an effective inference technique in commonsense reasoning are discussed.

Generating Negative Commonsense Knowledge

This work-in-progress paper shows empirically that obtaining meaningful negative samples for the completion task is nontrivial, and proposes NegatER, a framework for generating negative commonsense knowledge, to address this challenge.

The Curious Case of Commonsense Intelligence

Abstract Commonsense intelligence is a long-standing puzzle in AI. Despite considerable advances in deep learning, AI continues to be narrow and brittle due to its lack of common sense. Why is common

How Commonsense Knowledge Helps with Natural Language Tasks: A Survey of Recent Resources and Methodologies

An overview of commonsense reasoning in natural language processing, which requires a deeper understanding of the contexts and usually involves inference over implicit external knowledge, is given.

Machine Common Sense

This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions, based on real-life heuristics, developed through knowledge and experience of different generations.

Social Commonsense Reasoning with Multi-Head Knowledge Attention

This work proposes a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell, and is the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task.

Commonsense reasoning, commonsense knowledge, and the SP theory of intelligence

Why a fifth CSRK problem -- modelling how a chef may crack an egg into a bowl -- is beyond the capabilities of the SP System as it is now and how those deficiencies may be overcome via planned developments of the system.



Case-Based Reasoning

  • S. Craw
  • Computer Science
    Encyclopedia of Machine Learning and Data Mining
  • 2017
CBR is a term used in the fields of cognitive science and artificial intelligence for recalling cases that are similar to a target problem in order to help solve the problem.

Analogy, Intelligent IR, and Knowledge Integration for Intelligence Analysis

The goal is to discover interesting and powerful functional integrations that permit inferential, analogical, and intelligent IR technologies to exploit each others’ strengths to mitigate their weaknesses.

Knowledge in Action: Logical Foundations for Specifying and Implementing Dynamical Systems

When I started out as a newly hatched PhD student, one of the first articles I read and understood was Ray Reiter’s classic article on default logic, and I became fascinated by both default logic and, more generally, non-monotonic logics.

CYC: Using Common Sense Knowledge to Overcome Brittleness and Knowledge Acquisition Bottlenecks

The major limitations in building large software have always been its brittleness when confronted by problems that were not foreseen by its builders, and its bottlenecks can be widened.

Association for the Advancement of Artificial Intelligence

AIIDE is the premier conference on artificial intelligence in computer games and interactive entertainment that brings together technical leaders to examine how computer games can be improved using AI technologies, and to promote new approaches and commercial developments.

Surfaces and Essences: Analogy as the Fuel and Fire of Thinking

Prologue: Analogy as the Core of Cognition 1. The Evocation of Words 2. The Evocation of Phrases 3. A Vast Ocean of Invisible Analogies 4. Abstraction and Inter-category Sliding 5. How Analogies

Computational models of analogy.

Analogical mapping is a core process in human cognition, and there is now considerable consensus regarding the constraints governing the mapping process, but computational models still differ in their focus.

Using Golog for Deliberation and Team Coordination in Robotic Soccer

This paper reports on efforts to address issues to get robots to choose intelligently among various possible courses of actions within the framework of the Golog action language.