{"id":"https://openalex.org/W4412393358","doi":"https://doi.org/10.1145/3748324","title":"Computational Linguistic Approach to Orthographic Representation of Egyptian Arabic: Challenges and Implications","display_name":"Computational Linguistic Approach to Orthographic Representation of Egyptian Arabic: Challenges and Implications","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412393358","doi":"https://doi.org/10.1145/3748324"},"language":"en","primary_location":{"id":"doi:10.1145/3748324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748324","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/A5067503166","display_name":"Amany Fashwan","orcid":"https://orcid.org/0009-0005-8091-8405"},"institutions":[{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]},{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]}],"countries":["EG","US"],"is_corresponding":true,"raw_author_name":"Amany Fashwan","raw_affiliation_strings":["Linguistics and Phonetics Department, Alexandria University, Faculty of Arts","Linguistics and Phonetics Department, Alexandria University, Faculty of Arts, Alexandria, Egypt"],"affiliations":[{"raw_affiliation_string":"Linguistics and Phonetics Department, Alexandria University, Faculty of Arts","institution_ids":["https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Linguistics and Phonetics Department, Alexandria University, Faculty of Arts, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089945941","display_name":"Sameh Alansary","orcid":"https://orcid.org/0009-0007-2950-9555"},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG","US"],"is_corresponding":false,"raw_author_name":"Sameh Alansary","raw_affiliation_strings":["Linguistics and Phonetics Department, Alexandria University, Faculty of Arts","Linguistics and Phonetics Department, Alexandria University, Faculty of Arts, Alexandria, Egypt"],"affiliations":[{"raw_affiliation_string":"Linguistics and Phonetics Department, Alexandria University, Faculty of Arts","institution_ids":["https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Linguistics and Phonetics Department, Alexandria University, Faculty of Arts, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067503166"],"corresponding_institution_ids":["https://openalex.org/I1344076864","https://openalex.org/I84524832"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09277428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"9","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":0.9995999932289124,"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":0.9995999932289124,"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":0.9936000108718872,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9890999794006348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7725170850753784},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.7637604475021362},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.660027265548706},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6354703307151794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4615075886249542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44709131121635437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3531090021133423},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1654892861843109},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09909528493881226}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7725170850753784},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.7637604475021362},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.660027265548706},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6354703307151794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4615075886249542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44709131121635437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3531090021133423},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1654892861843109},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09909528493881226},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3748324","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2560280095","https://openalex.org/W2612649659","https://openalex.org/W2751193242","https://openalex.org/W2887428522","https://openalex.org/W3206143403","https://openalex.org/W4245193884","https://openalex.org/W4312698677","https://openalex.org/W4385573271","https://openalex.org/W4391156274","https://openalex.org/W4412282758","https://openalex.org/W6738700683"],"related_works":["https://openalex.org/W2384327295","https://openalex.org/W2004106894","https://openalex.org/W2363838046","https://openalex.org/W4249048193","https://openalex.org/W2358202658","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W3172144307","https://openalex.org/W4396855230","https://openalex.org/W3184247917"],"abstract_inverted_index":{"In":[0,87],"the":[1,13,39,43,73,92,112,136,141,149,160,185,219,225,230,242],"past,":[2],"Arabic":[3,108],"Dialects":[4],"(AD)":[5],"have":[6,25,45],"been":[7],"poorly":[8],"documented":[9],"linguistically":[10],"due":[11],"to":[12,56,101,159,239],"lack":[14,74],"of":[15,33,42,50,75,94,123,221,232,241],"written":[16],"forms":[17],"and":[18,38,52,72,132,153,176,196,201,236],"orthographies.":[19],"However,":[20],"in":[21,60,180,214],"recent":[22],"years,":[23],"AD":[24,79],"become":[26],"more":[27],"widely":[28],"used":[29],"as":[30,155,157,204],"a":[31,47,57,103,121,192,215],"means":[32],"communication":[34],"since":[35],"social":[36],"media":[37],"everywhere":[40],"availability":[41],"internet":[44],"created":[46],"massive":[48],"overflow":[49],"information":[51],"textual":[53],"data,":[54],"leading":[55],"growing":[58],"interest":[59],"Natural":[61],"Language":[62],"Processing":[63],"(NLP)":[64],"for":[65,78,84,106,114],"these":[66,198],"dialects.":[67],"The":[68],"highly":[69],"inflectional":[70],"morphology":[71],"standard":[76,96],"orthography":[77,97,143,183],"pose":[80],"an":[81],"important":[82],"challenge":[83],"NLP":[85],"work.":[86],"this":[88],"article,":[89],"we":[90,118,139,190,205],"handle":[91,140],"problem":[93,144],"lacking":[95],"during":[98,184],"our":[99,233],"work":[100],"build":[102],"morphological":[104,186,226,234,244],"analyzer":[105,235],"Egyptian":[107],"(EGY).":[109],"To":[110],"identify":[111],"guidelines":[113],"detecting":[115,181],"conventional":[116,142,150,182,207,210],"orthography,":[117],"depend":[119],"on":[120],"corpus":[122,137],"597,000":[124],"words":[125],"that":[126,217],"were":[127],"gathered":[128],"from":[129],"various":[130],"sources":[131],"genres.":[133],"While":[134],"analyzing":[135],"morphologically,":[138],"by":[145,224],"assigning":[146],"each":[147],"word":[148],"EGY":[151,161],"Lemma":[152],"stem":[154],"close":[156],"possible":[158],"pronunciation":[162],"no":[163],"matter":[164],"how":[165],"it":[166,238],"is":[167],"typically":[168],"written.":[169],"Nevertheless,":[170],"there":[171],"are":[172,212],"some":[173],"common":[174,199],"phenomena":[175,200],"complex":[177,202],"cases":[178,203],"involved":[179],"annotation":[187],"process.":[188],"Therefore,":[189],"take":[191],"closer":[193],"look":[194],"at":[195],"discuss":[197],"detect":[206],"orthography.":[208],"These":[209],"orthographies":[211],"represented":[213],"manner":[216],"facilitates":[218],"parsing":[220],"them":[222],"correctly":[223],"analyzer.":[227],"We":[228],"tested":[229],"coverage":[231],"compared":[237],"one":[240],"state-of-the-art":[243],"analyzers.":[245]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}