{"url":"/dataset/itacola","name":"ItaCoLA","full_name":null,"description_markdown":"**ItaCoLA** is a corpus for monolingual and cross-lingual acceptability judgments which contains almost 10,000 sentences with acceptability judgments.","description_withheld":null,"homepage":"https://github.com/dhfbk/ItaCoLA-dataset","introduced_date":"2021-09-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/monolingual-and-cross-lingual-acceptability","title":"Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus","first_author":"Daniela Trotta","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Linguistic Acceptability","url":"/task/linguistic-acceptability","datasets_with_task":"/datasets/task/linguistic-acceptability"}],"languages":[{"name":"Italian","url":"/datasets/language/italian"}],"variants":["ItaCoLA"],"data_loaders":[],"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-itacola","task":"Linguistic Acceptability","dataset_variant":"ItaCoLA","rows":4,"metrics":["MCC","Accuracy"],"first_row_in_archive_order":{"model":"XLM-R + TDA","paper":"/paper/acceptability-judgements-via-examining-the","metrics":{"Accuracy":"92.8","MCC":"0.683"},"code_links":[{"title":"danchern97/tda4la","url":"https://github.com/danchern97/tda4la"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/rucola-russian-corpus-of-linguistic","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","date":"2022-10-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","rows_on_this_dataset":2,"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."}