{"url":"/dataset/chid","name":"ChID","full_name":"Chinese IDiom dataset","description_markdown":"ChID is a large-scale Chinese IDiom dataset for cloze test. ChID contains 581K passages and 729K blanks, and covers multiple domains. In ChID, the idioms in a passage were replaced with blank symbols. For each blank, a list of candidate idioms including the golden idiom are provided as choice. \r\n\r\nSource: [ChID: A Large-scale Chinese IDiom Dataset for Cloze Test](https://arxiv.org/pdf/1906.01265v3.pdf)\r\nImage Source: [https://arxiv.org/pdf/1906.01265v3.pdf](https://arxiv.org/pdf/1906.01265v3.pdf)","description_withheld":null,"homepage":"https://github.com/chujiezheng/ChID-Dataset","introduced_date":"2019-06-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/chid-a-large-scale-chinese-idiom-dataset-for","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","first_author":"Chujie Zheng","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"},{"name":"Cloze (multi-choices) (Zero-Shot)","url":"/task/cloze-multi-choices-zero-shot","datasets_with_task":"/datasets/task/cloze-multi-choices-zero-shot"},{"name":"Cloze (multi-choices) (One-Shot)","url":"/task/cloze-multi-choices-one-shot","datasets_with_task":"/datasets/task/cloze-multi-choices-one-shot"},{"name":"Cloze (multi-choices) (Few-Shot)","url":"/task/cloze-multi-choices-few-shot","datasets_with_task":"/datasets/task/cloze-multi-choices-few-shot"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["ChID"],"data_loaders":[{"repo":"https://github.com/chujiezheng/ChID-Dataset","url":"https://github.com/chujiezheng/ChID-Dataset","frameworks":["tf"]}],"num_papers_in_archive":38,"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."}