Combining Machine Learning and Ontology: A Systematic Literature Review
This review synthesizes existing research on hybrid AI approaches, providing a structured overview for researchers interested in combining inductive and deductive reasoning, but it is incremental as it does not propose new methods.
The paper conducted a systematic literature review of 128 studies to explore techniques for integrating machine learning (inductive reasoning) and ontologies (deductive reasoning) in AI systems, identifying three main hybridization categories: learning-enhanced ontologies, semantic data mining, and learning and reasoning systems.
Motivated by the desire to explore the process of combining inductive and deductive reasoning, we conducted a systematic literature review of articles that investigate the integration of machine learning and ontologies. The objective was to identify diverse techniques that incorporate both inductive reasoning (performed by machine learning) and deductive reasoning (performed by ontologies) into artificial intelligence systems. Our review, which included the analysis of 128 studies, allowed us to identify three main categories of hybridization between machine learning and ontologies: learning-enhanced ontologies, semantic data mining, and learning and reasoning systems. We provide a comprehensive examination of all these categories, emphasizing the various machine learning algorithms utilized in the studies. Furthermore, we compared our classification with similar recent work in the field of hybrid AI and neuro-symbolic approaches.