Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG

Abstract

The overall AI trend of creating neuro-symbolic systems is reflected in the Semantic Web community with an increased interest in the development of systems that rely on both Semantic Web resources and Machine Learning components (SWeMLS, for short). However, understanding trends and best practices in this rapidly growing field is hampered by a lack of standardized descriptions of these systems and an annotated corpus of such systems. To address these gaps, we leverage the results of a large-scale systematic mapping study collecting information about 470 SWeMLS papers and formalize these into one resource containing: (i) the SWeMLS ontology, (ii) the SWeMLS pattern library containing machine-actionable descriptions of 45 frequently occurring SWeMLS workflows, and (iii) SWEMLS-KG, a knowledge graph including machine-actionable metadata of the papers in terms of the SWeMLS ontology. This resource provides the first framework for semantically describing and organizing SWeMLS thus making a key impact in (1) understanding the status quo of the field based on the published paper corpus and (2) enticing the uptake of machine-processable system documentation in the SWeMLS area.