RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation

TL;DR

RELRaE leverages large language models to extract, label, and evaluate relationships in XML schemas, facilitating the semi-automatic generation of ontologies for lab automation and data interoperability.

Contribution

The paper introduces a novel framework that uses LLMs for relationship extraction and labeling in XML schemas, enhancing ontology development processes.

Findings

LLMs can accurately generate relationship labels in XML schemas.

The framework improves semi-automatic ontology generation.

Effective use of LLMs supports lab data interoperability.

Abstract

A large volume of XML data is produced in experiments carried out by robots in laboratories. In order to support the interoperability of data between labs, there is a motivation to translate the XML data into a knowledge graph. A key stage of this process is the enrichment of the XML schema to lay the foundation of an ontology schema. To achieve this, we present the RELRaE framework, a framework that employs large language models in different stages to extract and accurately label the relationships implicitly present in the XML schema. We investigate the capability of LLMs to accurately generate these labels and then evaluate them. Our work demonstrates that LLMs can be effectively used to support the generation of relationship labels in the context of lab automation, and that they can play a valuable role within semi-automatic ontology generation frameworks more generally.