Top Level Ontology
Top-level ontologies provide a standardized, high-level framework for organizing and representing knowledge across diverse domains, aiming to improve data interoperability and facilitate knowledge sharing. Current research emphasizes using ontologies to enhance explainability in complex systems like multimodal large language models and to improve the efficiency of tasks such as ontology versioning and knowledge graph construction, often leveraging techniques like ontology matching and rule-based reasoning. This work has significant implications for various fields, enabling more robust and reliable AI systems, improved data management in scientific research, and more efficient knowledge discovery across diverse applications.
Papers
The Impact of Ontology on the Prediction of Cardiovascular Disease Compared to Machine Learning Algorithms
Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi, Hamza Ghandi, Mohamed Bahaj, Muhammad Raza Naqvi
Reasoning about concepts with LLMs: Inconsistencies abound
Rosario Uceda-Sosa, Karthikeyan Natesan Ramamurthy, Maria Chang, Moninder Singh
KNOW: A Real-World Ontology for Knowledge Capture with Large Language Models
Arto Bendiken
Grounding Realizable Entities
Michael Rabenberg, Carter Benson, Federico Donato, Yongqun He, Anthony Huffman, Shane Babcock, John Beverley
Capabilities: An Ontology
John Beverley, David Limbaugh, Eric Merrell, Peter M. Koch, Barry Smith
Fish-bone diagram of research issue: Gain a bird's-eye view on a specific research topic
JingHong Li, Huy Phan, Wen Gu, Koichi Ota, Shinobu Hasegawa