{"url":"/dataset/korsts","name":"KorSTS","full_name":null,"description_markdown":"**KorSTS** is a dataset for semantic textural similarity (STS) in Korean. The dataset is constructed by automatically the STS-B dataset. 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.\r\nThe KorSTS dataset comprises 5,749 training examples translated automatically and 2,879 evaluation examples translated manually.\r\n\r\nSource: [https://github.com/kakaobrain/KorNLUDatasets](https://github.com/kakaobrain/KorNLUDatasets)\r\nImage Source: [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":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"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":["KorSTS"],"data_loaders":[{"repo":"https://github.com/kakaobrain/KorNLUDatasets","url":"https://github.com/kakaobrain/KorNLUDatasets","frameworks":[]}],"num_papers_in_archive":13,"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."}