{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-diacritization-efficient-hierarchical","title":"Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization","arxiv_id":"2011.00538","date":"2020-11-01","proceeding":"COLING (WANLP) 2020 12","authors":["Badr AlKhamissi","Muhammad N. ElNokrashy","Mohamed Gabr"],"abstract":"We propose a novel architecture for labelling character sequences that achieves state-of-the-art results on the Tashkeela Arabic diacritization benchmark. The core is a two-level recurrence hierarchy that operates on the word and character levels separately---enabling faster training and inference than comparable traditional models. A cross-level attention module further connects the two, and opens the door for network interpretability. The task module is a softmax classifier that enumerates valid combinations of diacritics. This architecture can be extended with a recurrent decoder that optionally accepts priors from partially diacritized text, which improves results. We employ extra tricks such as sentence dropout and majority voting to further boost the final result. Our best model achieves a WER of 5.34%, outperforming the previous state-of-the-art with a 30.56% relative error reduction.","url_abs":"https://arxiv.org/abs/2011.00538v1","url_pdf":"https://arxiv.org/pdf/2011.00538v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-diacritization-efficient-hierarchical","repo_url":"https://github.com/BKHMSI/deep-diacritization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arabic-text-diacritization","task_name":"Arabic Text Diacritization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"single-headed-attention","method_name":"Single-Headed Attention"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arabic-text-diacritization-on-catt-dataset","task":"Arabic Text Diacritization","dataset":"CATT","model":"Deep Diacritization (D2)","rank_in_archive_order":6,"of":12,"metrics":{"DER(%)":"13.310","WER (%)":"49.417"},"uses_additional_data":false},{"leaderboard":"/sota/arabic-text-diacritization-on-catt-dataset","task":"Arabic Text Diacritization","dataset":"CATT","model":"Deep Diacritization (D3)","rank_in_archive_order":12,"of":12,"metrics":{"DER(%)":"58.313","WER (%)":"98.710"},"uses_additional_data":false},{"leaderboard":"/sota/arabic-text-diacritization-on-tashkeela-1","task":"Arabic Text Diacritization","dataset":"Tashkeela","model":"D3 (D2 + decoder)","rank_in_archive_order":3,"of":6,"metrics":{"Diacritic Error Rate":"0.0183","Word Error Rate (WER)":"0.0534"},"uses_additional_data":false},{"leaderboard":"/sota/arabic-text-diacritization-on-tashkeela-1","task":"Arabic Text Diacritization","dataset":"Tashkeela","model":"D2","rank_in_archive_order":4,"of":6,"metrics":{"Diacritic Error Rate":"0.0185","Word Error Rate (WER)":"0.0553"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2011.00538","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}