{"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/arabic-diacritics-in-the-wild-exploiting","title":"Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization","arxiv_id":"2406.05760","date":"2024-06-09","proceeding":null,"authors":["Salman Elgamal","Ossama Obeid","Tameem Kabbani","Go Inoue","Nizar Habash"],"abstract":"The widespread absence of diacritical marks in Arabic text poses a significant challenge for Arabic natural language processing (NLP). This paper explores instances of naturally occurring diacritics, referred to as \"diacritics in the wild,\" to unveil patterns and latent information across six diverse genres: news articles, novels, children's books, poetry, political documents, and ChatGPT outputs. We present a new annotated dataset that maps real-world partially diacritized words to their maximal full diacritization in context. Additionally, we propose extensions to the analyze-and-disambiguate approach in Arabic NLP to leverage these diacritics, resulting in notable improvements. Our contributions encompass a thorough analysis, valuable datasets, and an extended diacritization algorithm. We release our code and datasets as open source.","url_abs":"https://arxiv.org/abs/2406.05760v1","url_pdf":"https://arxiv.org/pdf/2406.05760v1.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":"arabic-diacritics-in-the-wild-exploiting","repo_url":"https://github.com/camel-lab/wild_diacritics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.05760","atlas_url":"https://app.syntology.ai/?focus=2406.05760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05760"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/CAMeL-Lab/wild_diacritics","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"6da8a04479bf42e1","entry":"determine_output_columns","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/evaluate.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6da8a04479bf42e1"}},{"code_sha256_prefix":"a39aab3f23931645","entry":"determine_output_columns","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/gen_predictions_sent.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/gen_predictions_sent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a39aab3f23931645"}},{"code_sha256_prefix":"b2902b3a09e667ab","entry":"group_genre_entries","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/prepare_wild2max.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/prepare_wild2max.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b2902b3a09e667ab"}},{"code_sha256_prefix":"39d226d76372810a","entry":"has_diac","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/wilddiacs_utils/modules/diac_handler/diac_handler.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/wilddiacs_utils/modules/diac_handler/diac_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"39d226d76372810a"}},{"code_sha256_prefix":"c5cdf233d710d8fe","entry":"is_number","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/wilddiacs_utils/modules/token_handler/token_handler.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/wilddiacs_utils/modules/token_handler/token_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c5cdf233d710d8fe"}},{"code_sha256_prefix":"a11786d0fd15ea70","entry":"parse_genre_path_args","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/evaluate.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a11786d0fd15ea70"}},{"code_sha256_prefix":"b90297accbec9ad0","entry":"process_args","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/evaluate.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b90297accbec9ad0"}},{"code_sha256_prefix":"08ba56361a829ac7","entry":"process_args","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/gen_predictions_sent.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/gen_predictions_sent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"08ba56361a829ac7"}},{"code_sha256_prefix":"1765b7b87e5d7e0e","entry":"singular_of_tanween","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/wilddiacs_utils/modules/diac_handler/diac_handler.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/wilddiacs_utils/modules/diac_handler/diac_handler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1765b7b87e5d7e0e"}},{"code_sha256_prefix":"eda525301a431887","entry":"gen_entries","repo":"CAMeL-Lab/wild_diacritics","repo_kind":"official","path":"code/exploiting_wilddiacs/prepare_wikinewsmax.py","file_url":"https://github.com/CAMeL-Lab/wild_diacritics/blob/HEAD/code/exploiting_wilddiacs/prepare_wikinewsmax.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"eda525301a431887"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}