Logo image
Back
Knowledge Graph Question Answering for Materials Science (KGQA4MAT)
Conference proceeding   Peer reviewed

Knowledge Graph Question Answering for Materials Science (KGQA4MAT)

Yuan An, Jane Greenberg, Fernando J. Uribe-Romo, Diego A. Gomez-Gualdron, Kyle Langlois, Jacob Furst, Alex Kalinowski, Xintong Zhao and Xiaohua Hu
METADATA AND SEMANTIC RESEARCH, MTSR 2023, v 2048, pp 18-29
01 Jan 2024
DOI: https://doi.org/10.1007/978-3-031-65990-4_2

Abstract

Computer Science, Information Systems Computer Science, Interdisciplinary Applications Information Science & Library Science Science & Technology Computer Science Technology
We present a study on Knowledge Graph Question Answering in Materials Science (KGQA4MAT), with a focus on metal-organic frameworks (MOFs). A knowledge graph for metal-organic frameworks (MOF-KG) has been constructed by integrating structured data, meta-data, and knowledge extracted from the literature. We aim to develop a natural language (NL) interface for domain expert to query the MOFKG. A first step is our benchmark, which consists of 161 complex questions involving comparison, aggregation, and intricate graph structures. Each question has been rephrased into three additional variations, totaling 644 questions and 161 KG queries. We then developed a systematic approach for utilizing ChatGPT to translate natural language questions into formal KG queries. We experimented with different prompt strategies. The research indicated that using an ontology, providing a few-shot examples, and offering a chain-of-thought explanation resulted in the top F1-score of 0.89. We also applied this method to the well-known QALD-9 dataset, achieving performance on par with the state-of-the-art techniques. The results indicate applicability of this model for MOF research and potentially other scientific foci.

Metrics

1 Record Views
5 citations in Web of Science

Details

Logo image