{"url":"/dataset/nakdimon-train","name":"Nakdimon-train","full_name":null,"description_markdown":"A collection of diacritized Hebrew text in a variety of registers and from different sources.","description_withheld":null,"homepage":"https://github.com/elazarg/hebrew_diacritized","introduced_date":"2021-05-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/restoring-hebrew-diacritics-without-a","title":"Restoring Hebrew Diacritics Without a Dictionary","first_author":"Elazar Gershuni","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Ancient Hebrew","url":"/datasets/language/ancient-hebrew"}],"variants":["Nakdimon-train"],"data_loaders":[],"num_papers_in_archive":1,"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."}