{"id":"https://openalex.org/W2997186977","doi":"https://doi.org/10.1145/3242177","title":"Diacritic-Based Matching of Arabic Words","display_name":"Diacritic-Based Matching of Arabic Words","publication_year":2018,"publication_date":"2018-12-14","ids":{"openalex":"https://openalex.org/W2997186977","doi":"https://doi.org/10.1145/3242177","mag":"2997186977"},"language":"en","primary_location":{"id":"doi:10.1145/3242177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242177","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/A5050418400","display_name":"Mustafa Jarrar","orcid":"https://orcid.org/0000-0003-4351-4207"},"institutions":[{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["PS"],"is_corresponding":true,"raw_author_name":"Mustafa Jarrar","raw_affiliation_strings":["Birzeit University, West Bank, Palestine"],"raw_orcid":"https://orcid.org/0000-0003-4351-4207","affiliations":[{"raw_affiliation_string":"Birzeit University, West Bank, Palestine","institution_ids":["https://openalex.org/I94800806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010806171","display_name":"Fadi A. Zaraket","orcid":"https://orcid.org/0000-0001-5909-6375"},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Fadi Zaraket","raw_affiliation_strings":["American University, Beirut, Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University, Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077286075","display_name":"Rami Asia","orcid":null},"institutions":[{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Rami Asia","raw_affiliation_strings":["Birzeit University, West Bank, Palestine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birzeit University, West Bank, Palestine","institution_ids":["https://openalex.org/I94800806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006202140","display_name":"Hamzeh Amayreh","orcid":"https://orcid.org/0000-0001-8408-7972"},"institutions":[{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Hamzeh Amayreh","raw_affiliation_strings":["Birzeit University, West Bank, Palestine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birzeit University, West Bank, Palestine","institution_ids":["https://openalex.org/I94800806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050418400"],"corresponding_institution_ids":["https://openalex.org/I94800806"],"apc_list":null,"apc_paid":null,"fwci":2.0301,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90264342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"18","issue":"2","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9973000288009644,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9905999898910522,"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":0.728504478931427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6007106900215149},{"id":"https://openalex.org/keywords/soundness","display_name":"Soundness","score":0.5843504071235657},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5556603670120239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458493828773499},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5157003998756409},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.48758620023727417},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4850456118583679},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45001640915870667},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.4473171830177307},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4392622113227844},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.43850553035736084},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.41754189133644104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3738918900489807},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32139575481414795},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.2664741277694702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1362113654613495},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08255761861801147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728504478931427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6007106900215149},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.5843504071235657},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5556603670120239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458493828773499},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5157003998756409},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.48758620023727417},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4850456118583679},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45001640915870667},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.4473171830177307},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4392622113227844},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.43850553035736084},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.41754189133644104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3738918900489807},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32139575481414795},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2664741277694702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1362113654613495},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08255761861801147},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242177","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":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313992","display_name":"Birzeit University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W125610139","https://openalex.org/W1030304353","https://openalex.org/W1504694836","https://openalex.org/W1557004199","https://openalex.org/W1993757038","https://openalex.org/W2012542894","https://openalex.org/W2020079054","https://openalex.org/W2054081167","https://openalex.org/W2056382745","https://openalex.org/W2057622292","https://openalex.org/W2079039075","https://openalex.org/W2117202778","https://openalex.org/W2125055259","https://openalex.org/W2126784811","https://openalex.org/W2132283323","https://openalex.org/W2136534344","https://openalex.org/W2136775334","https://openalex.org/W2169160736","https://openalex.org/W2249434041","https://openalex.org/W2250751111","https://openalex.org/W2313318480","https://openalex.org/W2484386651","https://openalex.org/W2560280095","https://openalex.org/W2740272870","https://openalex.org/W2791345409","https://openalex.org/W3104468439","https://openalex.org/W3123148474","https://openalex.org/W4205807230","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W13634261","https://openalex.org/W4250462479","https://openalex.org/W3163509751","https://openalex.org/W958050847","https://openalex.org/W2396405675","https://openalex.org/W175051304","https://openalex.org/W4402823833","https://openalex.org/W1549730417","https://openalex.org/W1548499332","https://openalex.org/W1994524667"],"abstract_inverted_index":{"Words":[0],"in":[1,33,158,162],"Arabic":[2,44,166],"consist":[3],"of":[4,24,98,105,115,132,149,165],"letters":[5],"and":[6,22,57,86,96,120,137,161],"short":[7],"vowel":[8],"symbols":[9],"called":[10],"diacritics":[11,17],"inscribed":[12],"atop":[13],"regular":[14],"letters.":[15],"Changing":[16],"may":[18],"change":[19],"the":[20,78,82,87,93,99,113,133,147,150],"syntax":[21],"semantics":[23],"a":[25,102,153],"word;":[26],"turning":[27],"it":[28],"into":[29],"another.":[30],"This":[31],"results":[32],"difficulties":[34],"when":[35],"comparing":[36],"words":[37,71],"based":[38],"solely":[39],"on":[40],"string":[41],"matching.":[42],"Typically,":[43],"NLP":[45],"applications":[46],"resort":[47],"to":[48,51,68,128],"morphological":[49],"analysis":[50],"battle":[52],"ambiguity":[53],"originating":[54],"from":[55],"this":[56,61],"other":[58],"challenges.":[59],"In":[60],"article,":[62],"we":[63],"introduce":[64],"three":[65],"alternative":[66],"algorithms":[67,100,151],"compare":[69],"two":[70],"with":[72],"possibly":[73],"different":[74],"diacritics.":[75],"We":[76,91,145],"propose":[77],"Subsume":[79,116,125,136],"knowledge-based":[80],"algorithm,":[81,85],"Imply":[83,118,138],"rule-based":[84],"Alike":[88,121,142],"machine-learning-based":[89],"algorithm.":[90],"evaluated":[92],"soundness,":[94],"completeness,":[95],"accuracy":[97,114],"against":[101],"large":[103],"dataset":[104],"86,886":[106],"word":[107],"pairs.":[108],"Our":[109],"evaluation":[110],"shows":[111],"that":[112],"(100%),":[117],"(99.32%),":[119],"(99.53%).":[122],"Although":[123],"accurate,":[124],"was":[126],"able":[127],"judge":[129],"only":[130],"75%":[131],"data.":[134],"Both":[135],"are":[139],"sound,":[140],"while":[141],"is":[143],"not.":[144],"demonstrate":[146],"utility":[148],"using":[152],"real-life":[154],"use":[155],"case":[156],"--":[157],"lemma":[159],"disambiguation":[160],"linking":[163],"hundreds":[164],"dictionaries.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
