Semantically-Linked Ontological Knowledge Extraction Graph For Domain-Specific Knowledge Discovery In Scientific Literature

The rapid growth of scientific papers presents several challenges for researchers, including information overload, data fragmentation, lack of standard terminology, and limited interoperability. These issues make it increasingly difficult to keep up with the literature and extract useful, field-specific information efficiently. To address these challenges, we introduce the semantically-linked ontological knowledge extraction framework, a tool that combines smart linking of concepts, flexible ontology building, and graph-based reasoning to organize and extract knowledge. This semantically-linked ontological knowledge extraction graph (SOKE Graph) leverages large-language models to extract domain-specific concepts from scientific articles, ensuring both semantic accuracy and adaptability to new data. These concepts are organized using an ontology—a structured framework of terms and relationships—that supports systematic data collection by grouping information into clearly defined layers. The resulting knowledge graph enables structured representation of extracted domain-specific information, allowing researchers to explore relationships between concepts and efficiently retrieve relevant data aligned with the objectives of this work. This approach allows SOKE Graph to find the connections between concepts and publications, and retrieve the most relevant studies in response to user questions. Initial evaluations of SOKE Graph show that it helps improve the accuracy of filtering high-relevance papers from large datasets compared to using only large-language models, and generates structured, interpretable outputs that facilitate data-driven insights. Moreover, this framework provides a robust and scalable artificial intelligence-based tool that accelerates literature analysis, guides decision-making, and helps researchers efficiently locate relevant information within complex scientific domains.