Programs with common sense

By John McCarthy. 1960

Subfields: Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Knowledge Graphs & Representation

Citations in the corpus

Finetuned Language Models Are Zero-Shot Learners (2021, background): “E.6 INSTRUCTIONS-BASED NLP Recent improvements in the capabilities of language models have led to increased interest in a nascent area of instructions-based NLP (Goldwasser & Roth, 2014, and see McCarthy (1960)).”
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (2019, background): “Early work sought programs that could reason about an environment in natural language (McCarthy, 1959), or leverage a world-model for deeper language understanding (Winograd, 1972).”
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark (2021, background): “In AI’s early years, researchers sought to build machines with common sense (McCarthy 1959); however, in the following decades, common sense came to be viewed as a near impossible goal.”
Logic meets Probability: Towards Explainable AI Systems for Uncertain Worlds (2017, background): “In a seminal paper, McCarthy [1958] put forward a profound idea to realize artiﬁcial intelligence (AI) systems: he posited that what the system needs to know could be represented in a formal language , and a general-purpose algorithm would then conclude the necessary actions needed to solve the…”
Ordinal Common-sense Inference (2016, background): “…Durme, 2013), systems that derive knowledge exclusively from such corpora may be more accurately considered models of language, rather than of the 2 McCarthy (1959): a program has common sense if it automatically deduces for itself a sufﬁciently wide class of immediate consequences of anything it…”
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language (2020, background): “A fundamental goal for AI, dating back to its earliest years, is automated reasoning: the ability to draw valid conclusions from explicitly provided knowledge (McCarthy, 1959).”
Why AI is harder than we think (2021, background): “There have been many attempts in the history of AI to give humanlike common sense to machines 1 , ranging from the logic-based approaches of John McCarthy [76] and Douglas Lenat [77] to today’s deep-learning-based approaches (e.g., [78]).”
Model-free, Model-based, and General Intelligence (2018, background): “…who was both the father of the most popular AI programming language at the time (Lisp) and the person that gave AI its name, was putting the basis for the logical approach to AI where the emphasis was not in the use of representations but in their expressiveness and semantics [McCarthy, 1958].”
Bridging the Gap: Converting Human Advice into Imagined Examples (2019, background): “Human advice has been recognized as a powerful source of guidance for learning systems since the early days of AI (McCarthy, 1959), and much work has been done on integrating advice into symbolic reasoning systems (Mostow, 1983; Golding et al., 1987; Myers, 1996).”
A Review on Language Models as Knowledge Bases (2022, background): “It has been a long-standing goal of AI to reason over explicit knowledge given to it in order to reach conclusions (McCarthy, 1959; Newell and Simon, 1956; Metaxiotis et al., 2002).”
Provably Bounded-Optimal Agents (1994, background): “In arti(cid:12)cial intelligence, the logical de(cid:12)nition of rationality, known in philosophy as the \practical syllogism", was put forward by McCarthy (1958), and reiterated strongly by Newell (1981).”
Three Modern Roles for Logic in AI (2020, methodology): “Portland, OR, USA. ACM, New York, NY, USA, 15 pages. https://doi.org/10.1145/3375395.3389131 1 INTRODUCTION Logic has played a fundamental role in artificial intelligence since the field was incepted [52]. This role has been mostly in the area of knowledge representation and reasoning, where logic i”