{"url":"/dataset/chip-sts","name":"CHIP-STS","full_name":"Semantic Textual Similarity Dataset","description_markdown":"CHIP Semantic Textual Similarity, a dataset for sentence similarity in the non-i.i.d.\r\n(non-independent and identically distributed) setting, is used for the CHIP-STS task. Specifically, the\r\ntask aims to transfer learning between disease types on Chinese disease questions and answer data.\r\nGiven question pairs related to 5 different diseases (The disease types in the training and testing set\r\nare different), the task intends to determine whether the semantics of the two sentences are similar.","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"}],"tasks":[{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CHIP-STS"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-similarity-on-chip-sts","task":"Semantic Similarity","dataset_variant":"CHIP-STS","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"MacBERT-large","paper":"/paper/cblue-a-chinese-biomedical-language","metrics":{"Macro F1":"85.6"},"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."}