@article{clinicaldocumentcorporaandassorteddomain, title = {Clinical Document Corpora and Assorted Domain Proxies: A Survey of Diversity in Corpus Design, with Focus on German Text Data}, author = {Udo Hahn}, year = {2024}, eprint = {2412.00230}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.00230v1}, }