From Metadata to Meaning: A Semantic Units Knowledge Graph for the Biodiversity Exploratories

TL;DR

This paper introduces Semantic Units in a biodiversity knowledge graph to improve user interaction and understanding, demonstrating how LLMs and embedding models can enhance metadata quality and support FAIR principles.

Contribution

It presents the first implementation of semantic units in a knowledge graph and explores their impact on querying and metadata enrichment using LLMs and embedding models.

Findings

Semantic units improve user comprehension of knowledge graphs.

Using LLMs and embeddings enhances metadata structuring and FAIR compliance.

Semantic units facilitate more meaningful and efficient querying.

Abstract

Knowledge Graphs (KGs) bear great potential for ecology and biodiversity researchers in their ability to support synthesis and integration efforts, meta-analyses, reasoning tasks, and overall machine interoperability of research data. However, this potential is yet to be realized as KGs are notoriously difficult to interact with via their query language SPARQL for many user groups alike. Additionally, a further hindrance for user-KG interaction is the fundamental disconnect between user requirements and requirements KGs have to fulfill regarding machine-interoperability, reasoning tasks, querying, and further technical requirements. Thus, many statements in a KG are of no semantic significance for end users. In this work, we investigate a potential remedy for this challenge: Semantic Units (SUs) are semantically significant, named subgraphs in a KG with the goal to enhance cognitive interoperability for users, and to provide responses to common KG modelling challenges. We model and construct a KG from publication and dataset metadata of the Biodiversity Exploratories (BE), a research platform for functional biodiversity research across research plots in Germany to contribute to biodiversity research from the perspective of computer science. We contribute further by delivering the first implementation of semantic units on a knowledge graph and investigate how SUs impact KG querying. Finally, we present two implementations of tasks that show how large language models (LLMs) can be used to extract structured metadata categories from publication and dataset titles and abstracts, and how embedding models can be used to enrich metadata with latent information, in an effort to support the creation of structured and FAIR (findable, accessible, interoperable, and reusable) metadata.