An Implementation of Ontology-Driven Reasoning for Conversational Question Answering over Knowledge Graphs
Abstract
This project presents an ontology-driven conversational question answering system over a hotel-domain knowledge graph, combining LLMs with symbolic reasoning for more reliable and structured retrieval. Natural-language questions are converted into Manchester Syntax queries, post-processed, and executed over an OWL knowledge graph enriched with property-chain axioms for implicit relations such as location and proximity. Retrieved entities are then summarized into natural-language responses using knowledge-graph-augmented generation. Evaluation on ten dialogues showed strong query performance, with nine achieving perfect retrieval overlap, while the final response stage still exhibited occasional omissions and hallucinations.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.