Commonsense reasoning and commonsense knowledge in artificial intelligence

By Ernest Davis, Gary F. Marcus. 2015

521 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

WinoGrande (2019, background): “Thus far, such systems are not robust when given examples that fall outside the data distribution that they were trained on (Gordon and Van Durme, 2013; Davis and Marcus, 2015; Schubert, 2015).”
A Hybrid Neural Network Model for Commonsense Reasoning (2019, methodology): “In this paper, we study two classic commonsense reasoning tasks: the Winograd Schema Challenge (WSC) and Pronoun Disambiguation Problem (PDP) (Levesque et al., 2011; Davis and Marcus, 2015).”
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models (2023, background): “, commonsense reasoning [11], Chain-of-Thought (CoT) is proposed to elicit the multi-step reasoning abilities of LLMs [42].”
From Recognition to Cognition: Visual Commonsense Reasoning (2018, background): “, inferring the likely intents, goals, and social dynamics of people) [13].”
Commonsense Knowledge Mining from Pretrained Models (2019, background): “Some have even argued that machine learning models cannot learn common sense implicitly (Davis and Marcus, 2015).”
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning (2020, background): “Commonsense reasoning, the ability to make acceptable and logical assumptions about ordinary scenes in our daily life, has long been acknowledged as a critical bottleneck of artiﬁcial intelligence and natural language processing (Davis and Marcus, 2015).”
Deep Learning: A Critical Appraisal (2018, background): “Another potential valuable place to look is human cognition (Davis & Marcus, 2015; Lake et al., 2016; Marcus, 2001; Pinker & Prince, 1988).”
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning (2020, background): “Commonsense reasoning is a critical component of any natural language understanding system (Davis and Marcus, 2015).”
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021, background): “Efforts in developing commonsense reasoning started as early as the foundation of the field of artificial intelligence (Grice, 1975; Winograd, 1972; Davis and Marcus, 2015; Minsky, 1975).”
Small Sample Learning in Big Data Era (2018, background): “, 2015), common sense (Davis and Marcus, 2015), and intuitive physics (Smith and Vul, 2013; Battaglia et al.”
Conversational Neuro-Symbolic Commonsense Reasoning (2020, background): “Projects like CYC [7], ConceptNet [8–10] and ATOMIC [11, 12] are examples of such KBs (see [2] for a comprehensive list).”
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning (2021, background): “challenge ML models to use various kinds of commonsense knowledge for solving tasks (Davis and Marcus, 2015).”
Natural Language Processing with Commonsense Knowledge: A Survey (2021, background): “Davis and Marcus [3] explored the challenges and importance of commonsense reasoning and knowledge in artificial intelligence, highlighting that despite advances in AI, progress in this area has been slow.”
Natural language processing: state of the art, current trends and challenges (2017, background): “In the recent past, models dealing with Visual Commonsense Reasoning [31] and NLP have also been getting attention of the several researchers and seems a promising and challenging area to work upon.”
Artificial Intelligence and Management: The Automation–Augmentation Paradox (2020, background): “Thisisparticularlytrueof managerialcontextscharacterizedbyhighdegreesof ambiguity,complexity,andrareevents,whichlimit deterministicapproaches ’ applicability (Davis & Marcus, 2015).”
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning (2019, background): “Empowering machines with the ability to perform commonsense reasoning has been seen as the bottleneck of artiﬁcial general intelligence (Davis and Marcus, 2015).”
Prerequisite Skills for Reading Comprehension: Multi-Perspective Analysis of MCTest Datasets and Systems (2017, methodology): “Commonsense reasoning is performed using taxonomic knowledge, qualitative knowledge, action, and event change, which we adopt from Davis and Marcus (2015).”