An approach based on open research knowledge graph for knowledge acquisition from scientific papers

Abstract

PurposeThis paper aims to curate open research knowledge graph (ORKG) with papers related to ontology learning and define an approach using ORKG as a computer-assisted tool to organize key-insights extracted from research papers.Design/methodology/approachAction research was used to explore, test and evaluate the use of the Open Research Knowledge Graph as a computer assistant tool for knowledge acquisition from scientific papers.FindingsTo extract, structure and describe research contributions, the granularity of information should be decided; to facilitate the comparison of scientific papers, one should design a common template that will be used to describe the state of the art of a domain.Originality/valueThis approach is currently used to document “food information engineering,” “tabular data to knowledge graph matching” and “question answering” research problems and the “neurosymbolic AI” domain. More than 200 papers are ingested in ORKG. From these papers, more than 800 contributions are documented and these contributions are used to build over 100 comparison tables. At the end of this work, we found that ORKG is a valuable tool that can reduce the working curve of state-of-the-art research.