COntExt: AI Framework for Context-Aware Ontology Extension from Operational Metrics
A recent paper published on arXiv (2607.29553) presents COntExt, a novel framework designed for context-aware ontology extension. This framework utilizes operational metric definitions to recommend the integration of referenced concepts and properties into current ontologies. It tackles the challenging and labor-intensive task of linking operational metric catalogs with ontological knowledge. COntExt breaks down the extension challenge into three components: predicting parent classes, determining relation types, and assigning data properties. The authors assessed various algorithms for these tasks across four cybersecurity ontologies. Classified as an 'AI' research contribution, the study emphasizes the convergence of artificial intelligence, knowledge representation, and cybersecurity, aiming to automate ontology enrichment by leveraging the context inherent in structured metric definitions.
Key facts
- COntExt is a framework for context-aware ontology extension from operational metrics.
- The framework takes structured metric definitions as input and suggests integration into existing ontologies.
- It defines three sub-tasks: parent class prediction, relation type prediction, and data property assignment.
- The evaluation was conducted across four cybersecurity ontologies.
- The paper is available on arXiv with ID 2607.29553.
- The research addresses the manual and labor-intensive process of connecting metric catalogues to ontologies.
- The framework utilizes the context of metrics to suggest ontology extensions.
- The paper is categorized as an AI research contribution.
Entities
Institutions
- arXiv