{"url":"/dataset/ggponc","name":"GGPONC","full_name":"German Guideline Program in Oncology NLP Corpus","description_markdown":"German Guideline Program in Oncology NLP Corpus (GGPONC) is a German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions.\r\n\r\nSource: [GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines](/paper/ggponc-a-corpus-of-german-medical-text-with)\r\nImage Source: [https://arxiv.org/pdf/2007.06400.pdf](https://arxiv.org/pdf/2007.06400.pdf)","description_withheld":null,"homepage":"https://github.com/JULIELab/GGPOnc","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ggponc-a-corpus-of-german-medical-text-with","title":"GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines","first_author":"Florian Borchert","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["GGPONC"],"data_loaders":[{"repo":"https://github.com/JULIELab/GGPOnc","url":"https://github.com/JULIELab/GGPOnc","frameworks":[]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}