{"url":"/dataset/cscd-ime","name":"CSCD-IME","full_name":null,"description_markdown":"Chinese Spelling Correction Dataset for errors generated by pinyin IME (CSCD-IME), a dataset containing 40,000 annotated sentences from real posts of official media on Sina Weibo. It is designed to detect and correct spelling mistakes in Chinese texts.\r\n\r\nSource: [CSCD-IME: Correcting Spelling Errors Generated by Pinyin IME](https://arxiv.org/pdf/2211.08788v1.pdf)\r\n\r\nImage Source: [https://github.com/nghuyong/cscd-ime](https://github.com/nghuyong/cscd-ime)","description_withheld":null,"homepage":"https://github.com/nghuyong/cscd-ime","introduced_date":"2022-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/cscd-ime-correcting-spelling-errors-generated","title":"CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers","first_author":"Yong Hu","url":null},"license":{"name":"MIT License","url":"https://github.com/nghuyong/cscd-ime/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Spelling Correction","url":"/task/spelling-correction","datasets_with_task":"/datasets/task/spelling-correction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CSCD-IME"],"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."}