{"url":"/dataset/cmeie","name":"CMeIE","full_name":"Chinese Medical Information Extraction Dataset","description_markdown":"Chinese Medical Information Extraction, a dataset that is also released in CHIP2020, is used for CMeIE task. The task is aimed at identifying both entities and relations in a sentence following the schema constraints. There are 53 relations defined in the dataset, including 10 synonymous sub-relationships and 43 other sub-relationships.","description_withheld":null,"homepage":"https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414","introduced_date":"2021-06-15","introduced_date_note":null,"introduced_by":null,"license":{"name":"@book{2020CMeIE,     title={CMeIE: Construction and Evaluation of Chinese Medical Information Extraction Dataset},      author={ Guan, T.  and  Zan, H. and Zhou, X. and Xu, H. and K Zhang},    publisher={Natural Language Processing and Chinese Computing, 9th CCF International Conference, NLPCC 2020, Zhengzhou, China, October 14–18, 2020, Proceedings, Part I},    year={2020}, }","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Medical Relation Extraction","url":"/task/medical-relation-extraction","datasets_with_task":"/datasets/task/medical-relation-extraction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CMeIE"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-relation-extraction-on-cmeie","task":"Medical Relation Extraction","dataset_variant":"CMeIE","rows":1,"metrics":["Micro F1"],"first_row_in_archive_order":{"model":"RoBERTa-wwm-ext-large","paper":"/paper/cblue-a-chinese-biomedical-language","metrics":{"Micro F1":"55.9"},"code_links":[{"title":"cbluebenchmark/cblue","url":"https://github.com/cbluebenchmark/cblue"},{"title":"freedomintelligence/sdak","url":"https://github.com/freedomintelligence/sdak"}]},"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."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":16,"samples_ran":4,"samples_unverified":12,"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."}