{"url":"/dataset/yaclc","name":"YACLC","full_name":"Yet Another Chinese Learner Corpus","description_markdown":"**YACLC** is a large scale, multidimensional annotated Chinese learner corpus. To construct the corpus, the aurhots first obtain a large number of topic-rich texts generated by Chinese as Foreign Language (CFL) learners. The authors collected and annotated 32,124 sentences written by CFL learners from the lang-8 platform. Each sentence is annotated by 10 annotators. After post processing, a total of 469,000 revised sentences are obtained.","description_withheld":null,"homepage":"http://cuge.baai.ac.cn/#/dataset?id=21&name=YACLC","introduced_date":"2021-12-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/yaclc-a-chinese-learner-corpus-with","title":"YACLC: A Chinese Learner Corpus with Multidimensional Annotation","first_author":"Yingying Wang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["YACLC"],"data_loaders":[],"num_papers_in_archive":5,"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."}