Developing a Natural Language Interface for Knowledge Graphs

Authors

• Ruth Assefa, Southern Methodist UniversityFollow
• Sarah Mendoza, Southern Methodist UniversityFollow
• Luke Voinov, Southern Methodist UniversityFollow
• Oyku Serap Ogut, Southern Methodist UniversityFollow
• Nurcan Yuruk, Southern Methodist UniversityFollow

Abstract

This paper proposes to solve the challenge of making databases more user-friendly by interfacing them with OpenAI's ChatGPT-3.5 model. We implemented this solution to assist researchers in easily finding others with similar research interests. Our study involves 184 researchers from 14 departments at Southern Methodist University (SMU). We collected researchers' areas of expertise and biographies and stored them in a Neo4j graph database. We used OpenAI's embedding models to create vector representations of the collected data, allowing for accurate similarity assessments via Neo4j's built-in algorithms. By integrating this system with LangChain, we enabled natural language queries. The results demonstrated high accuracy in identifying related researchers and potential inter-departmental collaborations. The AI interfacing provided an easy way for users to interact with the database.

Recommended Citation

R. Assefa, S. Mendoza, O. S. Ogut, L. Voinov, and N. Yuruk "Developing a Natural Language Interface for Knowledge Graphs," Southern Methodist University, Dallas, 2024.

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License