{"url":"/dataset/mcscset","name":"MCSCSet","full_name":null,"description_markdown":"**MCSCSet** is a large-scale specialist-annotated dataset, designed for the task of Medical-domain Chinese Spelling Correction that contains about 200k samples. MCSCSet involves: i) extensive real-world medical queries collected from Tencent Yidian, ii) corresponding misspelled sentences manually annotated by medical specialists.\r\n\r\nSource: [MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction](https://arxiv.org/pdf/2210.11720v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.11720v1.pdf](https://arxiv.org/pdf/2210.11720v1.pdf)","description_withheld":null,"homepage":"https://github.com/yzhihao/MCSCSet","introduced_date":"2022-10-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/mcscset-a-specialist-annotated-dataset-for","title":"MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction","first_author":"Wangjie Jiang","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/yzhihao/MCSCSet/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Spelling Correction","url":"/task/spelling-correction","datasets_with_task":"/datasets/task/spelling-correction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MCSCSet"],"data_loaders":[],"num_papers_in_archive":2,"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."}