{"url":"/dataset/dalaj","name":"DaLAJ","full_name":null,"description_markdown":"DaLAJ 1.0, a dataset for Linguistic Acceptability Judgments for Swedish, comprising 9,596 sentences in its first version; and the initial experiment using it for the binary classification task. DaLAJ is based on the SweLL second language learner data, consisting of essays at different levels of proficiency.","description_withheld":null,"homepage":"https://spraakbanken.gu.se/en/resources/dalaj-1-0","introduced_date":"2021-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/dalaj-a-dataset-for-linguistic-acceptability-1","title":"DaLAJ – a dataset for linguistic acceptability judgments for Swedish","first_author":"Elena Volodina","url":null},"license":{"name":"CC BY 4.0","url":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":"Swedish","url":"/datasets/language/swedish"}],"variants":["DaLAJ"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/linguistic-acceptability-on-dalaj","task":"Linguistic Acceptability","dataset_variant":"DaLAJ","rows":1,"metrics":["Accuracy","MCC"],"first_row_in_archive_order":{"model":"Sw-BERT + H0M","paper":"/paper/acceptability-judgements-via-examining-the","metrics":{"Accuracy":"76.9","MCC":"0.542"},"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/acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","rows_on_this_dataset":1,"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."}