{"id":"https://openalex.org/W2906891164","doi":"https://doi.org/10.21248/jlcl.32.2017.213","title":"A Survey and Comparative Study of Arabic Diacritization Tools","display_name":"A Survey and Comparative Study of Arabic Diacritization Tools","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2906891164","doi":"https://doi.org/10.21248/jlcl.32.2017.213","mag":"2906891164"},"language":"en","primary_location":{"id":"doi:10.21248/jlcl.32.2017.213","doi":"https://doi.org/10.21248/jlcl.32.2017.213","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.32.2017.213","pdf_url":"https://jlcl.org/article/download/213/211","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://jlcl.org/article/download/213/211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097494381","display_name":"Osaama Hamed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osaama Hamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072459546","display_name":"Torsten Zesch","orcid":"https://orcid.org/0000-0002-9678-3825","observed_orcids":["https://orcid.org/0000-0002-9678-3825"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torsten Zesch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7859,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.87655421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"32","issue":"1","first_page":"27","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14037","display_name":"Arabic Language Education Studies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic-diacritization","display_name":"Arabic diacritization","score":0.9959999918937683},{"id":"https://openalex.org/keywords/arabic-script","display_name":"Arabic script","score":0.46799999475479126},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.7289999723434448},{"id":"https://openalex.org/keywords/error-categories","display_name":"error categories","score":0.3619999885559082},{"id":"https://openalex.org/keywords/arabic-natural-language-processing","display_name":"Arabic language processing","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.75346839427948},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3756530284881592},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33783408999443054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29978761076927185},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.18308815360069275}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21248/jlcl.32.2017.213","doi":"https://doi.org/10.21248/jlcl.32.2017.213","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.32.2017.213","pdf_url":"https://jlcl.org/article/download/213/211","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:bibliographie.ub.uni-due.de:ubo_mods_00149820","doi":null,"is_oa":false,"landing_page_url":"https://jlcl.org/content/2-allissues/2-Heft1-2017/02-diacritics.pdf","pdf_url":"https://jlcl.org/content/2-allissues/2-Heft1-2017/02-diacritics.pdf","source":{"id":"https://openalex.org/S7407055102","display_name":"Universit\u00e4tsbibliographie, Universit\u00e4t Duisburg-Essen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:publikationen.ub.uni-frankfurt.de:83097","doi":null,"is_oa":true,"landing_page_url":"http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/83097","pdf_url":null,"source":{"id":"https://openalex.org/S4306400432","display_name":"Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114090438","host_organization_name":"Goethe University Frankfurt","host_organization_lineage":["https://openalex.org/I114090438"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.21248/jlcl.32.2017.213","doi":"https://doi.org/10.21248/jlcl.32.2017.213","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.32.2017.213","pdf_url":"https://jlcl.org/article/download/213/211","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2906891164.pdf","grobid_xml":"https://content.openalex.org/works/W2906891164.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W24746516","https://openalex.org/W33221268","https://openalex.org/W45643337","https://openalex.org/W125610139","https://openalex.org/W1553623403","https://openalex.org/W2012804051","https://openalex.org/W2041349462","https://openalex.org/W2041375131","https://openalex.org/W2054727018","https://openalex.org/W2057622292","https://openalex.org/W2065400286","https://openalex.org/W2100976324","https://openalex.org/W2102131353","https://openalex.org/W2109613320","https://openalex.org/W2118585731","https://openalex.org/W2132283323","https://openalex.org/W2136534344","https://openalex.org/W2147272182","https://openalex.org/W2147880316","https://openalex.org/W2153186553","https://openalex.org/W2185942205","https://openalex.org/W2188188178","https://openalex.org/W2250751111","https://openalex.org/W2250816155","https://openalex.org/W2251087009","https://openalex.org/W2412582921","https://openalex.org/W2493183125","https://openalex.org/W2575598244","https://openalex.org/W2585345551","https://openalex.org/W2740272870","https://openalex.org/W3202110839","https://openalex.org/W6890406761"],"related_works":["https://openalex.org/W4249048193","https://openalex.org/W3000360420","https://openalex.org/W3172144307","https://openalex.org/W3184247917","https://openalex.org/W4235657630","https://openalex.org/W2331401504","https://openalex.org/W2620283452","https://openalex.org/W2038219622","https://openalex.org/W566381545","https://openalex.org/W2955052790"],"abstract_inverted_index":{"Modern":[0],"Standard":[1],"Arabic,":[2],"as":[3,5,85,87],"well":[4,86],"other":[6],"languages":[7],"based":[8],"on":[9],"the":[10,54,59,63,66,77,91,110,130],"Arabic":[11,31,55],"script,":[12],"are":[13],"usually":[14],"written":[15],"without":[16],"diacritics,":[17],"which":[18],"complicates":[19],"many":[20,24],"language":[21],"processing":[22],"tasks.Although":[23],"different":[25,107],"approaches":[26],"for":[27,69,80,94],"automatic":[28],"diacritization":[29,56,81],"of":[30,100,112],"have":[32],"been":[33],"proposed,":[34],"it":[35],"is":[36,126],"still":[37],"unclear":[38],"what":[39],"performance":[40],"level":[41],"can":[42],"be":[43],"expected":[44],"in":[45,58,105,132],"a":[46,73,98],"practical":[47],"setting.For":[48],"that":[49,124],"purpose,":[50],"we":[51,115],"first":[52],"survey":[53],"tools":[57,79],"literature":[60],"and":[61,83,129],"group":[62],"results":[64],"by":[65],"corpus":[67],"used":[68],"testing.We":[70],"then":[71],"conduct":[72,116],"comparative":[74],"study":[75],"between":[76],"available":[78],"(Farasa":[82],"Madamira)":[84],"two":[88,106],"baselines.We":[89],"evaluate":[90],"error":[92,121],"rates":[93],"these":[95],"systems":[96],"using":[97],"set":[99],"publicly":[101],"available,":[102],"fully-diacritized":[103],"corpora":[104],"evaluation":[108],"modes.With":[109],"help":[111],"human":[113],"annotators,":[114],"an":[117],"additional":[118],"experiment":[119],"examining":[120],"categories.We":[122],"find":[123],"Farasa":[125],"outperforming":[127],"Madamira":[128],"baselines":[131],"both":[133],"modes.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
