{"url":"/dataset/lcqmc","name":"LCQMC","full_name":"Large-scale Chinese Question Matching Corpus","description_markdown":"**LCQMC** is a large-scale Chinese question matching corpus. LCQMC is more general than paraphrase corpus as it focuses on intent matching rather than paraphrase. The corpus contains 260,068 question pairs with manual annotation.","description_withheld":null,"homepage":"http://icrc.hitsz.edu.cn/info/1037/1146.htm","introduced_date":"2018-08-20","introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution 4.0 International License","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Chinese Sentence Pair Classification","url":"/task/chinese-sentence-pair-classification","datasets_with_task":"/datasets/task/chinese-sentence-pair-classification"},{"name":"Question Similarity","url":"/task/question-similarity","datasets_with_task":"/datasets/task/question-similarity"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":[],"data_loaders":[],"num_papers_in_archive":6,"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."}