{"url":"/task/arabic-text-diacritization","name":"Arabic Text Diacritization","slug":"arabic-text-diacritization","description_markdown":"Addition of diacritics for undiacritized arabic texts for words disambiguation.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":13,"papers_with_code":7,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/arabic-text-diacritization-on-catt-dataset","slug":"arabic-text-diacritization-on-catt-dataset","dataset":"CATT","dataset_url":"/dataset/catt-dataset","rows_in_archive":12,"metrics":["DER(%)","WER (%)"],"first_row_in_archive_order":{"model":"CATT ED","paper_title":"CATT: Character-based Arabic Tashkeel Transformer","paper_url":"/paper/catt-character-based-arabic-tashkeel","paper_date":"2024-07-03","arxiv_id":"2407.03236","code_links":[{"title":"abjadai/catt","url":"https://github.com/abjadai/catt"}],"syntology":null}},{"leaderboard":"/sota/arabic-text-diacritization-on-tashkeela-1","slug":"arabic-text-diacritization-on-tashkeela-1","dataset":"Tashkeela","dataset_url":"/dataset/arabic-text-diacritization","rows_in_archive":6,"metrics":["Diacritic Error Rate","Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"CBHG model","paper_title":"Effective Deep Learning Models for Automatic Diacritization of Arabic Text","paper_url":"/paper/effective-deep-learning-models-for-automatic","paper_date":"2020-11-01","arxiv_id":null,"code_links":[{"title":"almodhfer/Arabic_Diacritization","url":"https://github.com/almodhfer/Arabic_Diacritization"}],"syntology":null}}],"datasets":[{"url":"/dataset/arabic-text-diacritization","name":"Arabic Text Diacritization","full_name":null,"num_papers_in_archive":17},{"url":"/dataset/wikinews-dataset","name":"WikiNews Dataset","full_name":"WikiNews Arabic Diacritization Benchmark Dataset","num_papers_in_archive":6},{"url":"/dataset/catt-dataset","name":"CATT","full_name":"CATT Arabic Diacritization Benchmark Dataset","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":13,"items":[{"url":"/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","arxiv_id":"1911.03531","repositories_listed":2,"syntology":null},{"url":"/paper/190501965","title":"Arabic Text Diacritization Using Deep Neural Networks","date":"2019-04-25","arxiv_id":"1905.01965","repositories_listed":2,"syntology":null},{"url":"/paper/catt-character-based-arabic-tashkeel","title":"CATT: Character-based Arabic Tashkeel Transformer","date":"2024-07-03","arxiv_id":"2407.03236","repositories_listed":1,"syntology":null},{"url":"/paper/deep-diacritization-efficient-hierarchical","title":"Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization","date":"2020-11-01","arxiv_id":"2011.00538","repositories_listed":1,"syntology":null},{"url":"/paper/effective-deep-learning-models-for-automatic","title":"Effective Deep Learning Models for Automatic Diacritization of Arabic Text","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/camel-tools-an-open-source-python-toolkit-for","title":"CAMeL Tools: An Open Source Python Toolkit for Arabic Natural Language Processing","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-components-system-for-automatic-arabic","title":"Multi-components System for Automatic Arabic Diacritization","date":"2020-04-08","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}