{"id":"https://openalex.org/W4200130398","doi":"https://doi.org/10.1145/3486675","title":"Light Diacritic Restoration to Disambiguate Homographs in Modern Arabic Texts","display_name":"Light Diacritic Restoration to Disambiguate Homographs in Modern Arabic Texts","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4200130398","doi":"https://doi.org/10.1145/3486675"},"language":"en","primary_location":{"id":"doi:10.1145/3486675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486675","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/A5059302775","display_name":"Aqil M. Azmi","orcid":"https://orcid.org/0000-0002-0983-2861"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Aqil M. Azmi","raw_affiliation_strings":["King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006672167","display_name":"Rehab M. Alnefaie","orcid":null},"institutions":[{"id":"https://openalex.org/I142608572","display_name":"Prince Sattam Bin Abdulaziz University","ror":"https://ror.org/04jt46d36","country_code":"SA","type":"education","lineage":["https://openalex.org/I142608572"]},{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Rehab M. Alnefaie","raw_affiliation_strings":["King Saud University, Saudi Arabia and Prince Sattam bin Abdulaziz University, Al Kharj, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Saud University, Saudi Arabia and Prince Sattam bin Abdulaziz University, Al Kharj, Saudi Arabia","institution_ids":["https://openalex.org/I142608572","https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027010923","display_name":"Hatim Aboalsamh","orcid":"https://orcid.org/0000-0002-8000-5105"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatim A. Aboalsamh","raw_affiliation_strings":["King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5201,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73856346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/spelling","display_name":"Spelling","score":0.7015241980552673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6512272953987122},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5971869826316833},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5934866666793823},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5465686917304993},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5322555899620056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508394181728363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.502234935760498},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.4608973562717438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.45288801193237305},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4334249496459961},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4218288064002991},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4202152490615845},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1742570996284485},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17264235019683838},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08336931467056274},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06487396359443665}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7015241980552673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6512272953987122},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5971869826316833},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5934866666793823},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5465686917304993},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5322555899620056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508394181728363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.502234935760498},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.4608973562717438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45288801193237305},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4334249496459961},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4218288064002991},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4202152490615845},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1742570996284485},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17264235019683838},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08336931467056274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06487396359443665},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3486675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486675","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W30790492","https://openalex.org/W126531742","https://openalex.org/W207781496","https://openalex.org/W1484663152","https://openalex.org/W1524281572","https://openalex.org/W1972404024","https://openalex.org/W2022665088","https://openalex.org/W2041379403","https://openalex.org/W2132283323","https://openalex.org/W2214054931","https://openalex.org/W2413317570","https://openalex.org/W2525269154","https://openalex.org/W2581736217","https://openalex.org/W2583662888","https://openalex.org/W2612649659","https://openalex.org/W2676554382","https://openalex.org/W2767595811","https://openalex.org/W2783019390","https://openalex.org/W2885738119","https://openalex.org/W2890931798","https://openalex.org/W2906891164","https://openalex.org/W2909308233","https://openalex.org/W2921538177","https://openalex.org/W2957234659","https://openalex.org/W2960038063","https://openalex.org/W2968345023","https://openalex.org/W3043161732"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W4250167163","https://openalex.org/W4220791298"],"abstract_inverted_index":{"Diacritic":[0,50],"restoration":[1,51],"(also":[2],"known":[3],"as":[4,60],"diacritization":[5,69],"or":[6],"vowelization)":[7],"is":[8,22,52,94,121,166,179,211],"the":[9,13,63,66,78,100,111,117,130,139,145,149,198,201],"process":[10],"of":[11,31,62,70,84,114,125,141],"inserting":[12],"correct":[14],"diacritical":[15,32],"markings":[16,33],"into":[17],"a":[18,53,81,90,105,122,190],"text.":[19],"Modern":[20],"Arabic":[21],"typically":[23],"written":[24],"without":[25],"diacritics,":[26,115,153],"e.g.,":[27],"newspapers.":[28],"This":[29,102],"lack":[30],"often":[34],"causes":[35],"ambiguity,":[36],"and":[37,97,133,173,193,207],"though":[38],"natives":[39],"are":[40,45,74],"adept":[41],"at":[42],"resolving,":[43],"there":[44],"times":[46],"they":[47],"may":[48],"fail.":[49],"classical":[54],"problem":[55],"in":[56,76],"computer":[57],"science.":[58],"Still,":[59],"most":[61],"works":[64],"tackle":[65],"full":[67],"(heavy)":[68],"text,":[71],"we,":[72],"however,":[73],"interested":[75],"diacritizing":[77],"text":[79,93],"using":[80,110],"fewer":[82,152],"number":[83,113],"diacritics.":[85,187],"Studies":[86],"have":[87],"shown":[88],"that":[89,127,143],"fully":[91],"diacritized":[92],"visually":[95],"displeasing":[96],"slows":[98],"down":[99],"reading.":[101],"article":[103],"proposes":[104],"system":[106,169,202],"to":[107,181],"diacritize":[108],"homographs":[109],"least":[112],"thus":[116],"name":[118],"\u201clight.\u201d":[119],"There":[120],"large":[123],"class":[124,140],"words":[126,142],"fall":[128],"under":[129],"homograph":[131],"category,":[132],"we":[134,154,196],"will":[135],"be":[136],"dealing":[137],"with":[138],"share":[144],"spelling":[146],"but":[147],"not":[148,156],"meaning.":[150],"With":[151],"do":[155],"expect":[157],"any":[158],"effect":[159],"on":[160],"reading":[161],"speed,":[162],"while":[163],"eye":[164],"strain":[165],"reduced.":[167],"The":[168,176],"contains":[170],"morphological":[171,177],"analyzer":[172,178],"context":[174,194],"similarities.":[175],"used":[180],"generate":[182],"all":[183],"word":[184],"candidates":[185],"for":[186],"Then,":[188],"through":[189],"statistical":[191],"approach":[192],"similarities,":[195],"resolve":[197],"homographs.":[199],"Experimentally,":[200],"shows":[203],"very":[204],"promising":[205],"results,":[206],"our":[208],"best":[209],"accuracy":[210],"85.6%.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}
