Dr. Maria BIRYUKOV

Research Scientist at the Luxembourg Center for Contemporary and Digital History (C²DH).

Her research lies at the intersection of Natural Language Processing (NLP), Information Extraction (IE), and Knowledge Graph Engineering. She has developed extensible NLP pipelines for extracting and structuring knowledge from unstructured and semi-structured textual sources, and for integrating such knowledge with large graph resources such as YAGO, DBpedia, and Wikidata. Her work includes transforming millions of pages from the Luxembourg Business Registers into annotated structured data for expert analysis, as well as developing the NLP pipeline used to construct BioKB, a biomedical knowledge graph comprising more than 156 million edges at the time of its creation. She also previously developed an intelligent Information Retrieval system for educational applications in organic chemistry.

She taught Information Management I within the Bachelor in Computer Science (BiCS) programme, covering Databases and Information Retrieval. She has supervised Master’s and PhD students and served as a lecturer in the Master’s programme in Integrated Systems Biology.

She has contributed to interdisciplinary and applied research at the interface of computer science, digital humanities, biomedicine, and socio-economic data analysis. Her work has supported knowledge and technology transfer through collaborations with domain experts and through the application of AI- and NLP-based methods to large and heterogeneous text collections, including biomedical literature, historical archives, multilingual web resources, and corporate business archives. She has also contributed to exploratory research that informed the preparation of FNR-funded projects.

She received the SBV IMPROVER Network Verification Challenge Best Performer Award (2015), presented by Philip Morris International Biological Systems Research & Development, in recognition of outstanding performance in systems biology network verification.

She has held research and applied data science positions in Luxembourg and Belgium. From 2021 to 2024, she was Research Associate in the Department of Computer Science at the University of Luxembourg. From 2019 to 2020, she was Research Associate / Applied Data Scientist at the Luxembourg Centre for Contemporary and Digital History (C2DH), University of Luxembourg. From 2017 to 2019, she worked as Applied Data Scientist at Historical Consulting, Luxembourg. Earlier, from 2011 to 2017, she was Research Associate / Applied Data Scientist at the Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg. From 2005 to 2007, she worked as Research Assistant at the Facultés Universitaires de la Paix in Namur, Belgium. Since 2024, she has been working as an independent consultant in AI, Natural Language Processing, and data analysis.

She holds a PhD in Computer Science from the University of Luxembourg (2007–2010). Her doctoral dissertation, Methods for Extracting Meta-Information from Bibliographic Databases, was supervised by Prof. Dr. Christoph Schommer. She also holds an MA in Artificial Intelligence from the Katholieke Universiteit Leuven (2002–2004), where her Master’s thesis, Multi-Document Question Answering Text Summarization using Topic Signatures, was supervised by Prof. Dr. Marie-Francine Moens.