{"url":"/dataset/kornli","name":"KorNLI","full_name":null,"description_markdown":"**KorNLI** is a Korean Natural Language Inference (NLI) dataset. The dataset is constructed by automatically translating the training sets of the SNLI, XNLI and MNLI datasets. To ensure translation quality, two professional translators with at least seven years of experience who specialize in academic papers/books as well as business contracts post-edited a half of the dataset each and cross-checked each other’s translation afterward.\nIt contains 942,854 training examples translated automatically and 7,500 evaluation (development and test) examples translated manually\n\nSource: [https://github.com/kakaobrain/KorNLUDatasets](https://github.com/kakaobrain/KorNLUDatasets)","description_withheld":null,"homepage":"https://github.com/kakaobrain/KorNLUDatasets","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/kornli-and-korsts-new-benchmark-datasets-for","title":"KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding","first_author":"Jiyeon Ham","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"}],"languages":[{"name":"Korean","url":"/datasets/language/korean"}],"variants":["KorNLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/kakaobrain/kor_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/kor_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/kakaobrain/KorNLUDatasets","url":"https://github.com/kakaobrain/KorNLUDatasets","frameworks":[]}],"num_papers_in_archive":18,"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."}