{"id":"https://openalex.org/W4200304220","doi":"https://doi.org/10.1145/3470849","title":"Neural Arabic Text Diacritization: State-of-the-Art Results and a Novel Approach for Arabic NLP Downstream Tasks","display_name":"Neural Arabic Text Diacritization: State-of-the-Art Results and a Novel Approach for Arabic NLP Downstream Tasks","publication_year":2021,"publication_date":"2021-12-24","ids":{"openalex":"https://openalex.org/W4200304220","doi":"https://doi.org/10.1145/3470849"},"language":"en","primary_location":{"id":"doi:10.1145/3470849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3470849","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056848826","display_name":"Ali Fadel","orcid":"https://orcid.org/0000-0003-1360-130X"},"institutions":[{"id":"https://openalex.org/I156983542","display_name":"Jordan University of Science and Technology","ror":"https://ror.org/03y8mtb59","country_code":"JO","type":"education","lineage":["https://openalex.org/I156983542"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ali Fadel","raw_affiliation_strings":["Jordan University of Science and Technology, Irbid, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jordan University of Science and Technology, Irbid, Jordan","institution_ids":["https://openalex.org/I156983542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026238995","display_name":"Ibraheem Tuffaha","orcid":null},"institutions":[{"id":"https://openalex.org/I156983542","display_name":"Jordan University of Science and Technology","ror":"https://ror.org/03y8mtb59","country_code":"JO","type":"education","lineage":["https://openalex.org/I156983542"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ibraheem Tuffaha","raw_affiliation_strings":["Jordan University of Science and Technology, Irbid, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jordan University of Science and Technology, Irbid, Jordan","institution_ids":["https://openalex.org/I156983542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073474306","display_name":"Mahmoud Al\u2010Ayyoub","orcid":"https://orcid.org/0000-0001-9372-9076"},"institutions":[{"id":"https://openalex.org/I156983542","display_name":"Jordan University of Science and Technology","ror":"https://ror.org/03y8mtb59","country_code":"JO","type":"education","lineage":["https://openalex.org/I156983542"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Mahmoud Al-Ayyoub","raw_affiliation_strings":["Jordan University of Science and Technology, Irbid, Jordan"],"raw_orcid":"https://orcid.org/0000-0001-9372-9076","affiliations":[{"raw_affiliation_string":"Jordan University of Science and Technology, Irbid, Jordan","institution_ids":["https://openalex.org/I156983542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5597,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74494957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802634596824646},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7609706521034241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7504030466079712},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7161604166030884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7050601243972778},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6494361758232117},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5759905576705933},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.5574225187301636},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5561919808387756},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5155853629112244},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5010716915130615},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.49496859312057495},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4414634704589844},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4244282841682434},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4217471778392792},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4111039638519287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3499736785888672},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08270806074142456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802634596824646},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7609706521034241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7504030466079712},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7161604166030884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7050601243972778},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6494361758232117},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5759905576705933},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.5574225187301636},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5561919808387756},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5155853629112244},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5010716915130615},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.49496859312057495},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4414634704589844},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4244282841682434},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4217471778392792},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4111039638519287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3499736785888672},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08270806074142456},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3470849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3470849","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1598638450","https://openalex.org/W1940872118","https://openalex.org/W2012804051","https://openalex.org/W2056382745","https://openalex.org/W2057622292","https://openalex.org/W2132283323","https://openalex.org/W2146502635","https://openalex.org/W2187089797","https://openalex.org/W2239389665","https://openalex.org/W2250509225","https://openalex.org/W2250751111","https://openalex.org/W2342173569","https://openalex.org/W2398936787","https://openalex.org/W2472854096","https://openalex.org/W2493916176","https://openalex.org/W2585345551","https://openalex.org/W2625475744","https://openalex.org/W2739711390","https://openalex.org/W2740272870","https://openalex.org/W2767595811","https://openalex.org/W2770803436","https://openalex.org/W2783019390","https://openalex.org/W2785921341","https://openalex.org/W2794259165","https://openalex.org/W2897722020","https://openalex.org/W2902723393","https://openalex.org/W2957234659","https://openalex.org/W2962784628","https://openalex.org/W2966083394","https://openalex.org/W2970568224","https://openalex.org/W3010004153","https://openalex.org/W3080404591","https://openalex.org/W3105511060","https://openalex.org/W3112961516","https://openalex.org/W4394651511","https://openalex.org/W6640362995"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2114846443","https://openalex.org/W2093471820","https://openalex.org/W3102147106","https://openalex.org/W2347460059","https://openalex.org/W50079190","https://openalex.org/W3136048405","https://openalex.org/W182104056","https://openalex.org/W2160451571","https://openalex.org/W2794347674"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,87],"present":[4],"several":[5,35],"deep":[6],"learning":[7],"models":[8,17,51,67,76,99],"for":[9],"the":[10,55,62,98],"automatic":[11],"diacritization":[12],"of":[13,100],"Arabic":[14,92],"text.":[15],"Our":[16],"are":[18,52,68],"built":[19],"using":[20],"two":[21],"main":[22],"approaches,":[23],"viz.":[24],"Feed-Forward":[25],"Neural":[26,31],"Network":[27,32],"(FFNN)":[28],"and":[29,46,61,109,120],"Recurrent":[30],"(RNN),":[33],"with":[34,74],"enhancements":[36],"such":[37,104],"as":[38,105],"100-hot":[39],"encoding,":[40],"embeddings,":[41],"Conditional":[42],"Random":[43],"Field":[44],"(CRF),":[45],"Block-Normalized":[47],"Gradient":[48],"(BNG).":[49],"The":[50],"tested":[53],"on":[54,72],"only":[56],"freely":[57],"available":[58],"benchmark":[59],"dataset":[60],"results":[63],"show":[64,88],"that":[65],"our":[66],"either":[69],"better":[70],"or":[71],"par":[73],"other":[75],"even":[77],"those":[78],"requiring":[79],"human-crafted":[80],"language-dependent":[81],"post-processing":[82],"steps,":[83],"unlike":[84],"ours.":[85],"Moreover,":[86],"how":[89],"diacritics":[90],"in":[91],"can":[93],"be":[94],"used":[95],"to":[96],"enhance":[97],"downstream":[101],"NLP":[102],"tasks":[103],"Machine":[106],"Translation":[107,116],"(MT)":[108],"Sentiment":[110,121],"Analysis":[111],"(SA)":[112],"by":[113],"proposing":[114],"novel":[115],"over":[117,122],"Diacritization":[118,123],"(ToD)":[119],"(SoD)":[124],"approaches.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}