Work

Grounding From an AI and Cognitive Science Lens

Year: 2024

Type: article

Abstract: Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding, its significance for collaborative agents, and similarities and differences in grounding approaches in both communities. The article examines the potential of neurosymbolic approaches tailored for grounding tasks, showcasing how they can more comprehensively address grounding. Finally, we discuss areas for further exploration and development in grounding.

Source: IEEE Intelligent Systems

DOI: 10.1109/mis.2024.3366669

Authors: Goonmeet Bajaj, Valerie L. Shalin, Srinivasan Parthasarathy, Amit Sheth

Institutions: The Ohio State University, Wright State University, University of South Carolina

Language: English

Topic: Logic, Reasoning, and Knowledge

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: AI Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE), EAGER: Knowledge-guided neurosymbolic AI with guardrails for safe virtual health assistants