{"url":"/dataset/dareczech","name":"DaReCzech","full_name":"Dataset for text relevance ranking in Czech","description_markdown":"## DareCzech\r\n\r\nDaReCzech is a dataset for text relevance ranking in Czech. The dataset consists of more than 1.6M annotated query-documents pairs, which makes it one of the largest available datasets for this task.\r\n\r\n### Obtaining the Annotated Data\r\nPlease, first read [a disclaimer](https://github.com/seznam/DaReCzech/blob/master/disclaimer.md) that contains the terms of use. If you comply with them, send an email to [srch.vyzkum@firma.seznam.cz](mailto:srch.vyzkum@firma.seznam.cz) and the link to the dataset will be sent to you.","description_withheld":null,"homepage":"https://github.com/seznam/DaReCzech","introduced_date":"2021-12-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","first_author":"Matěj Kocián","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Document Ranking","url":"/task/document-ranking","datasets_with_task":"/datasets/task/document-ranking"}],"languages":[{"name":"Czech","url":"/datasets/language/czech"}],"variants":["DaReCzech"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-ranking-on-dareczech","task":"Document Ranking","dataset_variant":"DaReCzech","rows":3,"metrics":["P@10"],"first_row_in_archive_order":{"model":"Query-doc RobeCzech (Roberta-base)","paper":"/paper/siamese-bert-based-model-for-web-search","metrics":{"P@10":"46.73"},"code_links":[{"title":"seznam/dareczech","url":"https://github.com/seznam/dareczech"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","date":"2021-12-03","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"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."}