{"url":"/dataset/arabic-text-diacritization","name":"Arabic Text Diacritization","full_name":null,"description_markdown":"Extracted from the Tashkeela Corpus, the dataset consists of 55K lines containing about 2.3M words.\n\nSource: [https://github.com/AliOsm/arabic-text-diacritization](https://github.com/AliOsm/arabic-text-diacritization)","description_withheld":null,"homepage":"https://github.com/AliOsm/arabic-text-diacritization","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/190501965","title":"Arabic Text Diacritization Using Deep Neural Networks","first_author":"Ali Fadel","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Arabic Text Diacritization","url":"/task/arabic-text-diacritization","datasets_with_task":"/datasets/task/arabic-text-diacritization"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["Tashkeela","Arabic Text Diacritization"],"data_loaders":[{"repo":"https://github.com/AliOsm/arabic-text-diacritization","url":"https://github.com/AliOsm/arabic-text-diacritization","frameworks":[]}],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/arabic-text-diacritization-on-tashkeela-1","task":"Arabic Text Diacritization","dataset_variant":"Tashkeela","rows":6,"metrics":["Diacritic Error Rate","Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"CBHG model","paper":"/paper/effective-deep-learning-models-for-automatic","metrics":{"Diacritic Error Rate":"0.0113","Word Error Rate (WER)":"0.0443"},"code_links":[{"title":"almodhfer/Arabic_Diacritization","url":"https://github.com/almodhfer/Arabic_Diacritization"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/effective-deep-learning-models-for-automatic","title":"Effective Deep Learning Models for Automatic Diacritization of Arabic Text","date":"2020-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-diacritization-efficient-hierarchical","title":"Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization","date":"2020-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-components-system-for-automatic-arabic","title":"Multi-components System for Automatic Arabic Diacritization","date":"2020-04-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-arabic-text-diacritization-state-of-1","title":"Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation","date":"2019-11-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/190501965","title":"Arabic Text Diacritization Using Deep Neural Networks","date":"2019-04-25","rows_on_this_dataset":1,"code_links":2,"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."}