{"url":"/dataset/meddialog","name":"MedDialog","full_name":"MedDialog","description_markdown":"The MedDialog dataset (Chinese) contains conversations (in Chinese) between doctors and patients. It has 1.1 million dialogues and 4 million utterances. The data is continuously growing and more dialogues will be added. The raw dialogues are from haodf.com. All copyrights of the data belong to haodf.com.\r\n\r\nSource: [GitHub](https://github.com/UCSD-AI4H/Medical-Dialogue-System)","description_withheld":null,"homepage":"https://github.com/UCSD-AI4H/Medical-Dialogue-System","introduced_date":"2020-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/meddialog-a-large-scale-medical-dialogue","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","first_author":"Xuehai He","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MedDialog"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/UCSD26/medical_dialog","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/medical_dialog","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/UCSD-AI4H/Medical-Dialogue-System","url":"https://github.com/UCSD-AI4H/Medical-Dialogue-System","frameworks":[]}],"num_papers_in_archive":7,"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."}