Opening the Oberseminar Series with the Talk “Creating a Knowledge Graph for research in Humanities” by Dr. Vayianos Pertsas on 22.10
The video recording of the lecture is available online via the following link.
The lecture titled “Creating a Knowledge Graph for research in Humanities” will be given in-person by Dr. Vayianos Pertsas (Postdoctoral Researcher at Athens University of Economics and Business, Department of Informatics) at the opening of the oberseminar by HDSM on 22st October at 16:15.

Vayianos Pertsas holds a Dipl. Eng. Degree in Electrical and Computer Engineering from the University of Patras and a PhD degree in Informatics from the Athens University of Economics and Business. His research interests evolve around conceptual modeling and ontology population using information extraction techniques that mainly focus on leveraging linked data and its applications, along with NLP and machine learning techniques.
He has worked in the development of the NeDiMAH Methods Ontology in the ESF-funded Network for Digital Methods in the Arts and Humanities and in its evolution and operationalization in the form of the Scholarly Ontology. He has authored papers appearing in IJDL, ISWC, DH, TPDL, TWC, KEOD and co-tutored various workshops. He also teaches at the MSc Programme in Digital Methods for the Humanities, held by Athens University of Economics and Business, Department of Informatics.
The lecture will be conducted in TU Darmstadt, room S313/36. Public admission is only possible after registration. Please email Dr. Nadezhda Povroznik at povroznik@pg.tu-darmstadt.de to express your interest in attending the lecture.
The abstract of the lecture is as follows:
“Creating a Knowledge Graph for research in Humanities” by Dr. Vayianos Pertsas
The steep increase of research publications in every major discipline makes it increasingly difficult for experts to maintain an overview of their domain, increases the risk of missing new work or reinventing solutions, and makes it harder to relate ideas from different domains. Especially in multidisciplinary fields like Digital Humanities, it becomes notably harder to retrieve and interconnect knowledge from publications, particularly for cases of unstructured text from OCRed papers. This situation calls for new strategic reading methods that transform the essence of knowledge encoded in textual form into structured formats like Knowledge Graphs (KG), thus changing the way researchers engage with literature. In this lecture we present a digital workflow for creating such a KG from Humanities’ research publications through the identification, extraction and interrelation of entities based on Scholarly Ontology, a framework specifically designed for documenting scholarly work.
The entire pipeline regarding the transformation of research articles into a scholarly knowledge graph consists of three major phases: 1) Preprocessing, 2) Information Extraction and 3) Knowledge Graph Creation. Each phase can be further analyzed into various modules focusing on different func:onali:es of the workflow. These modules employ a combination of inference rules, heuristics as well as machine learning methods in order to perform tasks such as text parsing, segmentation and cleaning; entity extraction, entity disambiguation, relation extraction; entity linking, metadata mapping and instance creation. Overall, the
pipeline employs a modular architecture that takes as input unstructured OCRed text from research articles and yields a scholarly knowledge graph in the output.
The digital workflow presented in this lecture enables the extraction of semantically complex (and of variable length) en::es like research activities, goals, methods and findings, deals with unstructured -OCRed- text, while focusing on the domain of Humani:es research. In addition, the extraction of semantic relationships between the extracted entities allows for beZer understanding and representation of their semantic context (e.g. the research process during which a method was employed, the reason for its employment, etc.). The produced KG allows for answering semantically complex queries such as: “find all the references of the articles containing activities that deal with 3D Reconstruction” or “retrieve the findings of the articles that have as reference a specific DOI”, etc.

OpenEdition suggests that you cite this post as follows:
valentinaprishchepova (October 14, 2024). Opening the Oberseminar Series with the Talk “Creating a Knowledge Graph for research in Humanities” by Dr. Vayianos Pertsas on 22.10. HDSM. Retrieved February 15, 2026 from https://hdsm.hypotheses.org/3692