{"url":"/dataset/cmeee","name":"CMeEE","full_name":"Chinese Medical Named Entity Recognition Dataset","description_markdown":"Chinese Medical Named Entity Recognition, a dataset first released in CHIP20204, is used for CMeEE task. Given a pre-defined schema, the task is to identify and extract entities from the given sentence and classify them into nine categories: disease, clinical manifestations, drugs, medical equipment, medical procedures, body, medical examinations, microorganisms, and department.","description_withheld":null,"homepage":"https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414","introduced_date":"2021-06-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","first_author":"Ningyu Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CMeEE"],"data_loaders":[],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-cmeee","task":"Named Entity Recognition (NER)","dataset_variant":"CMeEE","rows":2,"metrics":["F1","Micro F1"],"first_row_in_archive_order":{"model":"BERT-CRF (Replicated in AdaSeq)","paper":"/paper/improving-named-entity-recognition-by","metrics":{"F1":"68.97"},"code_links":[{"title":"modelscope/adaseq","url":"https://github.com/modelscope/adaseq"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/RaNER"},{"title":"Alibaba-NLP/CLNER","url":"https://github.com/Alibaba-NLP/CLNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":4,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":20,"samples_ran":4,"samples_unverified":16,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}