{"id":"https://openalex.org/W3013971782","doi":"https://doi.org/10.1109/cdma47397.2020.00007","title":"Attention-Based Sequence Learning Model for Arabic Diacritic Restoration","display_name":"Attention-Based Sequence Learning Model for Arabic Diacritic Restoration","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3013971782","doi":"https://doi.org/10.1109/cdma47397.2020.00007","mag":"3013971782"},"language":"en","primary_location":{"id":"doi:10.1109/cdma47397.2020.00007","doi":"https://doi.org/10.1109/cdma47397.2020.00007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdma47397.2020.00007","pdf_url":null,"source":{"id":"https://openalex.org/S7407106641","display_name":"International Conference on Data Science and Machine Learning Applications (CDMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 6th Conference on Data Science and Machine Learning Applications (CDMA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5016221575","display_name":"Ali Alkhathlan","orcid":"https://orcid.org/0000-0002-0715-3363","observed_orcids":["https://orcid.org/0000-0002-0715-3363"]},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ali Alkhatlan","raw_affiliation_strings":["Department of Computer Science, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034394212","display_name":"Faris Kateb","orcid":"https://orcid.org/0000-0003-3226-5583","observed_orcids":["https://orcid.org/0000-0003-3226-5583"]},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Faris Kateb","raw_affiliation_strings":["Department of Computer Science, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049180880","display_name":"Jugal Kumar Kalita","orcid":"https://orcid.org/0000-0002-8765-7018","observed_orcids":["https://orcid.org/0000-0002-8765-7018"]},"institutions":[{"id":"https://openalex.org/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jugal Kalita","raw_affiliation_strings":["Department of Computer Science, University of Colorado at Colorado Springs, Colorado, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado at Colorado Springs, Colorado, USA","institution_ids":["https://openalex.org/I888729015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5599,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68392549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9750999808311462,"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":0.9750999808311462,"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/T10028","display_name":"Topic Modeling","score":0.011900000274181366,"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":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.796999990940094},{"id":"https://openalex.org/keywords/gated-recurrent-unit","display_name":"gated recurrent unit","score":0.9079999923706055},{"id":"https://openalex.org/keywords/sequence-to-sequence-models","display_name":"sequence-to-sequence models","score":0.8349999785423279},{"id":"https://openalex.org/keywords/arabic-text","display_name":"Arabic text","score":0.3240000009536743},{"id":"https://openalex.org/keywords/online-texts","display_name":"online texts","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8330734372138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8316183090209961},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6771907806396484},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6682625412940979},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6514176726341248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246323585510254},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5669848322868347},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5176784992218018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36116406321525574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34897464513778687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2658555507659912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2315249741077423},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdma47397.2020.00007","doi":"https://doi.org/10.1109/cdma47397.2020.00007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdma47397.2020.00007","pdf_url":null,"source":{"id":"https://openalex.org/S7407106641","display_name":"International Conference on Data Science and Machine Learning Applications (CDMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 6th Conference on Data Science and Machine Learning Applications (CDMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W125610139","https://openalex.org/W144571221","https://openalex.org/W1498436455","https://openalex.org/W1924770834","https://openalex.org/W2012804051","https://openalex.org/W2020079054","https://openalex.org/W2041349462","https://openalex.org/W2056382745","https://openalex.org/W2057622292","https://openalex.org/W2063116544","https://openalex.org/W2064675550","https://openalex.org/W2065400286","https://openalex.org/W2075647637","https://openalex.org/W2095705004","https://openalex.org/W2109613320","https://openalex.org/W2136534344","https://openalex.org/W2153186553","https://openalex.org/W2185942205","https://openalex.org/W2250509225","https://openalex.org/W2250732891","https://openalex.org/W2250751111","https://openalex.org/W2250816155","https://openalex.org/W2251545731","https://openalex.org/W2472854096","https://openalex.org/W2517194566","https://openalex.org/W2609300251","https://openalex.org/W2739702159","https://openalex.org/W2740272870","https://openalex.org/W2757205734","https://openalex.org/W2772633765","https://openalex.org/W2783019390","https://openalex.org/W2800726910","https://openalex.org/W2884001105","https://openalex.org/W2885738119","https://openalex.org/W2900975931","https://openalex.org/W2969262604","https://openalex.org/W3104127158","https://openalex.org/W6629815555"],"related_works":["https://openalex.org/W3008803645","https://openalex.org/W7215664476","https://openalex.org/W3033823513","https://openalex.org/W2807585093","https://openalex.org/W4313207819","https://openalex.org/W2945888757","https://openalex.org/W3015320364","https://openalex.org/W2995505957","https://openalex.org/W2884119403","https://openalex.org/W2963500086"],"abstract_inverted_index":{"Diacritic":[0,137],"restoration":[1],"is":[2],"a":[3,29],"fundamental":[4],"issue":[5],"in":[6],"many":[7],"languages":[8,26],"such":[9,53],"as":[10,54],"Arabic,":[11],"Greek":[12],"and":[13,33,59,61,143],"others.":[14],"The":[15],"bulk":[16],"of":[17,92,150],"online":[18],"texts":[19],"lack":[20],"these":[21,25,81],"markings.":[22],"This":[23,95],"makes":[24],"difficult":[27],"for":[28,45],"human":[30],"to":[31,98,103,147],"interpret":[32],"computer":[34],"process.":[35],"In":[36,106],"this":[37,100,107],"work,":[38,108],"we":[39,109],"will":[40],"automatically":[41],"restore":[42],"the":[43,46,111,125,136,148,151],"diacritics":[44],"Arabic":[47],"language.":[48],"Previous":[49],"sequence-to-sequence":[50],"based":[51],"approaches":[52],"Abandah":[55],"et":[56],"al.,":[57],"[1],":[58],"Belinkov":[60],"Glass":[62],"[2]":[63],"have":[64],"been":[65],"used.":[66],"These":[67],"use":[68],"Recurrent":[69],"Neural":[70],"Network":[71],"(RNN)":[72],"involving":[73,119],"Long-":[74],"Short":[75],"Term":[76],"Memory":[77],"(LSTM)":[78],"models.":[79],"Interestingly,":[80],"are":[82],"language-independent,":[83],"avoiding":[84],"any":[85,90],"morphological,":[86],"syntactical":[87],"analysis":[88],"or":[89],"type":[91],"external":[93],"resources.":[94],"approach":[96],"leads":[97],"making":[99],"model":[101,128,134],"agnostic":[102],"new":[104],"languages.":[105],"extend":[110],"previous":[112],"work":[113],"with":[114,129],"an":[115],"alternate":[116],"RNN":[117,127],"architecture":[118],"Gated-Recurrent":[120],"Units":[121],"(GRU).":[122],"We":[123],"augment":[124],"basic":[126],"attention-based":[130],"mechanisms.":[131],"Our":[132],"GRU-attentive":[133],"improved":[135],"Error":[138],"Rate":[139],"(DER)":[140],"by":[141,144],"0.19%":[142],"2.32%":[145],"compared":[146],"state":[149],"art.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-04-03T00:00:00"}