Our Staff - Interdisciplinary Expertise for the Social Sciences

The many faces of GESIS

Knowledge Technologies for the Social Sciences
Information and Data Retrieval

+49 (0221) 47694-731
John•Culbert[at]gesis•org
vCard

Vita

Jack Culbert (a.k.a. John) is a research associate in the team Information and Data Retrieval (IDR) situated in the department of Knowledge Technologies for the Social Sciences (KTS).

Jack graduated from the university of Nottingham with a Masters degree in Mathematics focusing on pure mathematics, computation and statistics. He has experience research and development and consulting for the development of Natural Language Processing, Machine Learning and Knowledge Graph systems from his previous employment as a Senior AI&ML Engineer at Roke and Data Scientist at Arca Blanca.

Jack is particularly interested in NLP based Information Extraction technologies, including Entity Recognition, Coreference Resolution, Relationship Extraction and Entity Linking, as well as machine learning technologies such as Large Language Models, Attention Networks and Graph Neural Networks for Classification, Extraction, Link Inference and Sentiment Analysis and Explainable AI.

Publications

Working and discussion paper

Culbert, Jack, Philipp Mayr, Najko Jahn, Nick Haupka, and Alexander Schneidermann. 2024. Analysis of the Publication and Document Types in OpenAlex, Web of Science, Scopus, Pubmed and Semantic Scholar. ArXiV Preprint. doi: https://doi.org/10.48550/ARXIV.2406.15154. https://arxiv.org/abs/2406.15154.

Culbert, Jack, Philipp Mayr-Schlegel, Anne Hobert, Najko Jahn, Nick Haupka, Marion Schmidt, and Paul Donner. 2024. Reference Coverage Analysis of OpenAlex compared to Web of Science and Scopus. doi: https://doi.org/10.48550/arXiv.2401.16359. https://arxiv.org/abs/2401.16359.

Tong, Xu, Nina Smirnova, Sharmila Upadhyaya, Ran Yu, Chao Sun, Jack Culbert, Wolfgang Otto, and Philipp Mayr. 2024. Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study. doi: https://doi.org/10.48550/arXiv.2408.13501.

Culbert, Jack. 2023. 4TCT: A 4chan Text Collection Tool. ArXiV Preprint. doi: https://doi.org/10.48550/arXiv.2307.03556. https://github.com/jhculb/4TCT.

Data/Software

Culbert, Jack, Nina Smirnova, and Philipp Mayr-Schlegel. 2024. Indo-German Literature Dataset. doi: https://doi.org/10.5281/ZENODO.10607235. https://zenodo.org/records/10607235.

Culbert, Jack, Philipp Mayr, Solanki Gupta, Anurag Kanaujia, Hiran H. Lathabai, and Vivek Kumar Singh. 2024. Open AI Literature 2010-2020 Dataset. doi: https://doi.org/10.5281/zenodo.10997450.

Presentation not at a conference

Culbert, Jack. 2024. "The Reference Coverage Analysis of OpenAlex compared to WoS and Scopus." Broadening Data Sources for Bibliometric Analyses: Recent Results and Further Developments, Hcéres, Paris, 2024-02-29. doi: https://doi.org/10.5281/zenodo.10777335. https://zenodo.org/records/10777335.