{"id":"https://openalex.org/W4408982575","doi":"https://doi.org/10.36824/2022-graf-gutk","title":"Graphemic Normalization of the Perso-Arabic Script","display_name":"Graphemic Normalization of the Perso-Arabic Script","publication_year":2025,"publication_date":"2025-03-30","ids":{"openalex":"https://openalex.org/W4408982575","doi":"https://doi.org/10.36824/2022-graf-gutk"},"language":"en","primary_location":{"id":"doi:10.36824/2022-graf-gutk","doi":"https://doi.org/10.36824/2022-graf-gutk","is_oa":true,"landing_page_url":"https://doi.org/10.36824/2022-graf-gutk","pdf_url":null,"source":{"id":"https://openalex.org/S4210181686","display_name":"Grapholinguistics and its applications","issn_l":"2534-5192","issn":["2534-5192","2681-8566"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grapholinguistics and Its Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.36824/2022-graf-gutk","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062396507","display_name":"Raiomond Doctor","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raiomond Doctor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029193854","display_name":"Alexander Gutkin","orcid":"https://orcid.org/0000-0001-6327-4824","observed_orcids":["https://orcid.org/0000-0001-6327-4824"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Gutkin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063164740","display_name":"Cibu Johny","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cibu Johny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark A","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Roark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196","observed_orcids":["https://orcid.org/0000-0002-9040-5196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Sproat","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":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.03995953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"315","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0019000000320374966,"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/T10028","display_name":"Topic Modeling","score":0.0007999999797903001,"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/perso-arabic-script","display_name":"Perso-Arabic script","score":0.9440000057220459},{"id":"https://openalex.org/keywords/arabic-script","display_name":"Arabic script","score":0.5860000252723694},{"id":"https://openalex.org/keywords/arabic-text-processing","display_name":"Arabic text processing","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7974861264228821},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7637454271316528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217952370643616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5625388622283936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46771472692489624},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36923980712890625},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.07989510893821716},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04132005572319031},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.36824/2022-graf-gutk","doi":"https://doi.org/10.36824/2022-graf-gutk","is_oa":true,"landing_page_url":"https://doi.org/10.36824/2022-graf-gutk","pdf_url":null,"source":{"id":"https://openalex.org/S4210181686","display_name":"Grapholinguistics and its applications","issn_l":"2534-5192","issn":["2534-5192","2681-8566"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grapholinguistics and Its Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.12273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.12273","pdf_url":"https://arxiv.org/pdf/2210.12273","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2210.12273","doi":"https://doi.org/10.48550/arxiv.2210.12273","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.12273","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.36824/2022-graf-gutk","doi":"https://doi.org/10.36824/2022-graf-gutk","is_oa":true,"landing_page_url":"https://doi.org/10.36824/2022-graf-gutk","pdf_url":null,"source":{"id":"https://openalex.org/S4210181686","display_name":"Grapholinguistics and its applications","issn_l":"2534-5192","issn":["2534-5192","2681-8566"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grapholinguistics and Its Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385574296","https://openalex.org/W4385571195","https://openalex.org/W4386566362","https://openalex.org/W2558850127","https://openalex.org/W2053751574","https://openalex.org/W4206850324","https://openalex.org/W7172494932","https://openalex.org/W152945032","https://openalex.org/W612633176","https://openalex.org/W7096013556"],"abstract_inverted_index":{"Since":[0],"its":[1],"original":[2,36],"appearance":[3],"in":[4,10,75,146,165,167],"1991,":[5],"the":[6,35,47,53,66,73,90,100,108,113,118,134,147,172],"Perso-Arabic":[7,50,148,187],"script":[8,137,149,188],"representation":[9,185],"Unicode":[11],"has":[12],"grown":[13],"from":[14,104,142],"169":[15],"to":[16],"over":[17,23],"440":[18],"atomic":[19],"isolated":[20],"characters":[21],"spread":[22],"several":[24],"code":[25],"pages":[26],"representing":[27],"standard":[28],"letters,":[29],"various":[30],"diacritics":[31],"and":[32,38,59,99,125,154,184],"punctuation":[33],"for":[34,170,200,209],"Arabic":[37,58],"numerous":[39],"other":[40],"regional":[41,191],"orthographic":[42,130,192],"traditions.":[43],"This":[44],"paper":[45],"documents":[46],"challenges":[48],"that":[49,181],"presents":[51],"beyond":[52],"best-documented":[54],"languages,":[55],"such":[56,88],"as":[57,89],"Persian,":[60],"building":[61],"on":[62,72,139,151],"earlier":[63],"work":[64],"by":[65,83],"expert":[67],"community.":[68],"We":[69,132,179],"particularly":[70],"focus":[71],"situation":[74],"natural":[76],"language":[77,144,156],"processing":[78],"(NLP),":[79],"which":[80],"is":[81,177,198],"affected":[82],"multiple,":[84],"often":[85],"neglected,":[86],"issues":[87],"use":[91],"of":[92,102,115,120,129,136,186,203,214],"visually":[93],"ambiguous":[94],"yet":[95],"canonically":[96],"nonequivalent":[97],"letters":[98,103],"mixing":[101],"different":[105],"orthographies.":[106],"Among":[107],"contributing":[109],"conflating":[110],"factors":[111],"are":[112,196],"lack":[114,128],"input":[116],"methods,":[117],"instability":[119],"modern":[121,204],"orthographies,":[122],"insufficient":[123],"literacy,":[124],"loss":[126],"or":[127],"tradition.":[131],"evaluate":[133],"effects":[135],"normalization":[138,176],"eight":[140],"languages":[141,173,210],"diverse":[143],"families":[145],"diaspora":[150],"machine":[152],"translation":[153],"statistical":[155],"modeling":[157],"tasks.":[158],"Our":[159],"results":[160],"indicate":[161],"statistically":[162],"significant":[163],"improvements":[164],"performance":[166],"most":[168],"conditions":[169],"all":[171],"considered":[174],"when":[175],"applied.":[178],"argue":[180],"better":[182],"understanding":[183],"variation":[189],"within":[190],"traditions,":[193],"where":[194],"those":[195],"present,":[197],"crucial":[199],"further":[201],"progress":[202],"computational":[205],"NLP":[206],"techniques":[207],"especially":[208],"with":[211],"a":[212],"paucity":[213],"resources.":[215]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-03-31T00:00:00"}