{"url":"/dataset/kor-lang8","name":"Kor-Lang8","full_name":"Lang-8 Korean Corpus","description_markdown":"**Kor-Lang8** is a Korean grammatical error correction (GEC) dataset extracted from the NAIST Lang-8 Learner Corpora by the language label. It contains more than 109K sentence pairs.\r\n\r\nSource: [Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation](https://arxiv.org/pdf/2210.14389v2.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.14389v2.pdf](https://arxiv.org/pdf/2210.14389v2.pdf)","description_withheld":null,"homepage":"https://github.com/soyoung97/Standard_Korean_GEC","introduced_date":"2022-10-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-standardizing-korean-grammatical","title":"Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation","first_author":"Soyoung Yoon","url":null},"license":null,"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":"Korean","url":"/datasets/language/korean"}],"variants":["Kor-Lang8"],"data_loaders":[],"num_papers_in_archive":1,"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."}