{"url":"/dataset/mucgec","name":"MuCGEC","full_name":"Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction","description_markdown":"MuCGEC is a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7,063 sentences collected from three different Chinese-as-a-Second-Language (CSL) learner sources. Each sentence has been corrected by three annotators, and their corrections are meticulously reviewed by an expert, resulting in 2.3 references per sentence.","description_withheld":null,"homepage":"https://github.com/HillZhang1999/MuCGEC","introduced_date":"2022-04-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/mucgec-a-multi-reference-multi-source-1","title":"MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction","first_author":"Yue Zhang","url":null},"license":{"name":"Apache-2.0","url":"https://github.com/HillZhang1999/MuCGEC/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Grammatical Error Correction","url":"/task/grammatical-error-correction","datasets_with_task":"/datasets/task/grammatical-error-correction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MuCGEC"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/grammatical-error-correction-on-mucgec","task":"Grammatical Error Correction","dataset_variant":"MuCGEC","rows":1,"metrics":["F0.5"],"first_row_in_archive_order":{"model":"GEC-DI (LM+GED)","paper":"/paper/improving-seq2seq-grammatical-error","metrics":{"F0.5":"48.61"},"code_links":[{"title":"Jacob-Zhou/gecdi","url":"https://github.com/Jacob-Zhou/gecdi"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/improving-seq2seq-grammatical-error","title":"Improving Seq2Seq Grammatical Error Correction via Decoding Interventions","date":"2023-10-23","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}