RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation
This work addresses interoperability issues in lab automation by enabling semi-automatic ontology generation, though it is incremental as it applies existing LLM methods to a new domain.
The paper tackles the problem of translating XML data from robot experiments into knowledge graphs by enriching XML schemas for ontology generation, and demonstrates that large language models can effectively extract and label relationships, supporting semi-automatic ontology frameworks.
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.