{"url":"/dataset/rucola","name":"RuCoLA","full_name":null,"description_markdown":"The **Russian Corpus of Linguistic Acceptability (RuCoLA)** is built from the ground up under the well-established binary LA approach. RuCoLA consists of 9.8k in-domain sentences from linguistic publications and 3.6k out-of-domain sentence produced by generative models.\r\n\r\nSource: [RuCoLA: Russian Corpus of Linguistic Acceptability](https://arxiv.org/pdf/2210.12814v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.12814v1.pdf](https://arxiv.org/pdf/2210.12814v1.pdf)","description_withheld":null,"homepage":"https://github.com/RussianNLP/RuCoLA","introduced_date":"2022-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","first_author":"Vladislav Mikhailov","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Linguistic Acceptability","url":"/task/linguistic-acceptability","datasets_with_task":"/datasets/task/linguistic-acceptability"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["RuCoLA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nthngdy/rucola","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/linguistic-acceptability-on-rucola","task":"Linguistic Acceptability","dataset_variant":"RuCoLA","rows":9,"metrics":["MCC","Accuracy"],"first_row_in_archive_order":{"model":"Ru-RoBERTa+TDA","paper":"/paper/can-bert-eat-rucola-topological-data-analysis","metrics":{"Accuracy":"85.7","MCC":"0.594"},"code_links":[{"title":"upunaprosk/la-tda","url":"https://github.com/upunaprosk/la-tda/blob/master/5_Head_importance.ipynb"},{"title":"upunaprosk/la-tda","url":"https://github.com/upunaprosk/la-tda"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/can-bert-eat-rucola-topological-data-analysis","title":"Can BERT eat RuCoLA? Topological Data Analysis to Explain","date":"2023-04-04","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","date":"2022-10-23","rows_on_this_dataset":7,"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."}