Ontology Matching (OM), is a critical task in knowledge integration, where aligning heterogeneous ontologies facilitates data interoperability and knowledge sharing. Traditional OM systems often rely on expert knowledge or predictive models, with limited exploration of the potential of Large Language Models (LLMs). We present the LLMs4OM framework, a novel approach to evaluate the effectiveness of LLMs in OM tasks. This framework utilizes two modules for retrieval and matching, respectively, enhanced by zero-shot prompting across three ontology representations: concept, concept-parent, and concept-children. Through comprehensive evaluations using 20 OM datasets from various domains, we demonstrate that LLMs, under the LLMs4OM framework, can match and even surpass the performance of traditional OM systems, particularly in complex matching scenarios. Our results highlight the potential of LLMs to significantly contribute to the field of OM.

To cope with the growing number of multimedia assets on smartphones and social media, an integrated approach for semantic indexing and retrieval is required. Here, we introduce a generic framework to fuse existing image and video analysis tools and algorithms into a unified semantic annotation, indexing and retrieval model resulting in a multimedia feature vector graph representing various levels of media content, media structures and media features. Utilizing artificial intelligence (AI) and machine learning (ML), these feature representations can provide accurate semantic indexing and retrieval. Here, we provide an overview of the generic multimedia analysis framework (GMAF) and the definition of a multimedia feature vector graph framework (MMFVGF). We also introduce AI4MMRA to detect differences, enhance semantics and refine weights in the feature vector graph. To address particular requirements on smartphones, we introduce an algorithm for fast indexing and retrieval of graph structures. Experiments to prove efficiency, effectiveness and quality of the algorithm are included. All in all, we describe a solution for highly flexible semantic indexing and retrieval that offers unique potential for applications such as social media or local applications on smartphones.

The frameworks which have been established since the start of the NFDI allow for a coordinated development of RDM services, which include the introduction of community specific Terminology Services. To address the challenge of alignment and re-use of established ontologies and terminologies in the engineering domain, a Terminology Service (TS) was set-up for the NFDI4Ing initiative: https://terminology.nfdi4ing.de. The NFDI4Ing TS provides a single point of access to relevant research concepts and offers the building blocks for (meta-) data schemata and data annotation. As an open source platform, it features more than 50 ontologies, 147,000 terms and over 5,800 properties from a range of engineering-related terminology collections. The use of the NFDI4Ing TS fosters interoperability and reuse in a FAIR data context.

The Ontology Development Tracker (OnDeT) has been developed to facilitate the computation and interactive exploration of differences between multiple versions of a Git-hosted ontology throughout its temporal evolution. Existing tools focus primarily on pairwise comparisons, which limits the ability to analyze the entire evalutionary history of the ontology. OnDeT addresses this limitation by integrating three existing tools for pairwise comparisons between ontologies. Based on changes have been made to the ontology, the OnDeT tool captures and processes differences between different versions of the same ontology. A comprehensive user interface allows users to examine and explore differences in chronological order, as well as to explore specific differences based on a selected class name and dates. In addition, a semantic representation of these differences has been developed using the Provenance Ontology (PROV-O) specification. The OnDeT Knowledge Graph (KG) leverages this representation to provide a detailed semantic overview of all differences. OnDeT is integrated into the Technische Informationsbibliothek (TIB) Terminology Service (TS). Finally, to validate its correctness, OnDeT was evaluated using reasoners and a series of competency questions.

Ontology Matching (OM), is a critical task in knowledge integration, where aligning heterogeneous ontologies facilitates data interoperability and knowledge sharing. Traditional OM systems often rely on expert knowledge or predictive models, with limited exploration of the potential of Large Language Models (LLMs). We present the LLMs4OM framework, a novel approach to evaluate the effectiveness of LLMs in OM tasks. This framework utilizes two modules for retrieval and matching, respectively, enhanced by zero-shot prompting across three ontology representations: concept, concept-parent, and concept-children. Through comprehensive evaluations using 20 OM datasets from various domains, we demonstrate that LLMs, under the LLMs4OM framework, can match and even surpass the performance of traditional OM systems, particularly in complex matching scenarios. Our results highlight the potential of LLMs to significantly contribute to the field of OM.