Research Process Knowledge Graph Extraction from Publications
Publication "Research Process Knowledge Graph Extraction from Publications" in Springer Nature Computer Science by Vayianos Pertsas & Panos Constantopoulos from the Department of Informatics at Athens University of Economics and Business
Research Fellow Vayianos Pertsas and Emeritus Professor Panos Constantopoulos, from the Department of Informatics at the Athens University of Economics and Business (AUEB), are authors of a scientific article recently published in the prestigious international journal Springer Nature Computer Science, titled: "Research Process Knowledge Graph Extraction from Publications".
A digital workflow for creating knowledge graphs (KG) is presented in the paper describing research processes by extracting relevant entities and relations from the text of publications, associating them with publication metadata and exporting the output as Resource Description Framework (RDF) triples adhering to Linked Data standards. The authors experimented with Convolutional Neural Networks (CNN), transformer-based binary classifiers; a two-stage pipeline implementation comprising a transformer-based text classifier, which predicts whether a sentence contains the entities sought, in tandem with a transformer-based entity recognizer for finding the boundaries of the entities inside the sentences that contain them; and Large Language Model (LLM) prompting techniques.
The entire workflow is ontology-driven, based on Scholarly Ontology, specifically designed for documenting scholarly work.
