{"id":"https://openalex.org/W4385574296","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.36","title":"Beyond Arabic: Software for Perso-Arabic Script Manipulation","display_name":"Beyond Arabic: Software for Perso-Arabic Script Manipulation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385574296","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.36"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.36","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.36","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.36","pdf_url":"https://aclanthology.org/2022.wanlp-1.36.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.wanlp-1.36.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Alexander Gutkin","raw_affiliation_strings":["Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","Google Research \u2020 United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]},{"raw_affiliation_string":"Google Research \u2020 United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063164740","display_name":"Cibu Johny","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Cibu Johny","raw_affiliation_strings":["Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","Google Research \u2020 United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]},{"raw_affiliation_string":"Google Research \u2020 United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062396507","display_name":"Raiomond Doctor","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Raiomond Doctor","raw_affiliation_strings":["Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","India \u2022 United States \u229b Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]},{"raw_affiliation_string":"India \u2022 United States \u229b Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark A","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Brian Roark","raw_affiliation_strings":["Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","Google Research \u2020 United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]},{"raw_affiliation_string":"Google Research \u2020 United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]},{"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":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Richard Sproat","raw_affiliation_strings":["Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","Google Research \u2020 United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research \u2020 United Kingdom India \u2022 United States \u229b Japan","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]},{"raw_affiliation_string":"Google Research \u2020 United Kingdom","institution_ids":["https://openalex.org/I4210113297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4147,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62533923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9667999744415283,"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":0.9667999744415283,"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":0.021299999207258224,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/perso-arabic-script","display_name":"Perso-Arabic script","score":0.9900000095367432},{"id":"https://openalex.org/keywords/finite-state-transducers","display_name":"finite-state transducers","score":0.9879999756813049},{"id":"https://openalex.org/keywords/visual-invariance","display_name":"visual invariance","score":0.8830000162124634},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.8920000195503235},{"id":"https://openalex.org/keywords/transliteration","display_name":"transliteration","score":1.0},{"id":"https://openalex.org/keywords/character-typology","display_name":"character typology","score":0.7689999938011169},{"id":"https://openalex.org/keywords/open-source-library","display_name":"open-source library","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.7991914749145508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898458242416382},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.6088164448738098},{"id":"https://openalex.org/C2777323237","wikidata":"https://www.wikidata.org/wiki/Q1828555","display_name":"Arabic script","level":3,"score":0.564673125743866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5390505194664001},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5055391788482666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49088388681411743},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4617161452770233},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4453080892562866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42326340079307556},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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:10.18653/v1/2022.wanlp-1.36","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.36","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.36","pdf_url":"https://aclanthology.org/2022.wanlp-1.36.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.11406","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.11406","pdf_url":"https://arxiv.org/pdf/2301.11406","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.11406","doi":"https://doi.org/10.48550/arxiv.2301.11406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.11406","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:10.18653/v1/2022.wanlp-1.36","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.36","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.36","pdf_url":"https://aclanthology.org/2022.wanlp-1.36.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385574296.pdf","grobid_xml":"https://content.openalex.org/works/W4385574296.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W813927053","https://openalex.org/W1572758415","https://openalex.org/W1582482241","https://openalex.org/W1629199664","https://openalex.org/W1923758913","https://openalex.org/W2068291762","https://openalex.org/W2100000146","https://openalex.org/W2250865262","https://openalex.org/W2465720142","https://openalex.org/W2516386219","https://openalex.org/W2626693266","https://openalex.org/W2786156794","https://openalex.org/W2807459182","https://openalex.org/W2904958475","https://openalex.org/W2939248936","https://openalex.org/W3003356185","https://openalex.org/W3029344629","https://openalex.org/W3103525021","https://openalex.org/W3104475289","https://openalex.org/W3120975640","https://openalex.org/W3137010024","https://openalex.org/W3149349258","https://openalex.org/W3156496359","https://openalex.org/W4211051852","https://openalex.org/W4280494215","https://openalex.org/W4285790281","https://openalex.org/W4287887882","https://openalex.org/W4408982575"],"related_works":["https://openalex.org/W4408982575","https://openalex.org/W1535983216","https://openalex.org/W4385571195","https://openalex.org/W182782441","https://openalex.org/W1506882074","https://openalex.org/W2053751574","https://openalex.org/W2103834034","https://openalex.org/W7100284945","https://openalex.org/W2166660646","https://openalex.org/W2007071873"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"open-source":[4],"software":[5],"library":[6,77],"that":[7,26,42,56,105,128],"provides":[8,79],"a":[9,135,140,147],"set":[10],"of":[11,24,35,61,91],"finite-state":[12],"transducer":[13],"(FST)":[14],"components":[15],"and":[16,44,83],"corresponding":[17],"utilities":[18],"for":[19,69,125,138],"manipulating":[20],"the":[21,28,47,58,66,89,103,112,130],"writing":[22],"systems":[23],"languages":[25,72,104],"use":[27,106],"Perso-Arabic":[29,92],"script.The":[30],"operations":[31,41],"include":[32],"various":[33],"levels":[34],"script":[36,114,141],"normalization,":[37],"including":[38],"visual":[39,59],"invariance-preserving":[40],"subsume":[43],"go":[45],"beyond":[46],"standard":[48],"Unicode":[49,99],"normalization":[50],"forms,":[51],"as":[52,54],"well":[53],"transformations":[55],"modify":[57],"appearance":[60],"characters":[62,93],"in":[63],"accordance":[64],"with":[65],"regional":[67],"orthographies":[68],"eleven":[70],"contemporary":[71],"from":[73,98],"diverse":[74],"language":[75,127],"families.The":[76],"also":[78],"simple":[80],"FST-based":[81],"romanization":[82],"transliteration.We":[84],"additionally":[85],"attempt":[86],"to":[87,102,146],"formalize":[88],"typology":[90],"by":[94,144],"providing":[95,134],"one-to-many":[96],"mappings":[97],"code":[100],"points":[101],"them.While":[107],"our":[108],"work":[109],"focuses":[110],"on":[111],"Arabic":[113,118,131],"diaspora":[115],"rather":[116],"than":[117],"itself,":[119],"this":[120],"approach":[121],"could":[122],"be":[123],"adopted":[124],"any":[126],"uses":[129],"script,":[132],"thus":[133],"unified":[136],"framework":[137],"treating":[139],"family":[142],"used":[143],"close":[145],"billion":[148],"people.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-08-05T00:00:00"}