{"id":"https://openalex.org/W7139939356","doi":"https://doi.org/10.1016/j.procs.2026.01.086","title":"Advances of Informal to Formal Persian Text Conversion: A Survey","display_name":"Advances of Informal to Formal Persian Text Conversion: A Survey","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139939356","doi":"https://doi.org/10.1016/j.procs.2026.01.086"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.086","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.086","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.086","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099853020","display_name":"Aylin Naebzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Aylin Naebzadeh","raw_affiliation_strings":["Department of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130241577","display_name":"Maryam Hashemi","orcid":null},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Maryam Hashemi","raw_affiliation_strings":["Department of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086716685","display_name":"Sauleh Eetemadi","orcid":"https://orcid.org/0000-0003-1376-2023"},"institutions":[{"id":"https://openalex.org/I132806614","display_name":"University of Dubai","ror":"https://ror.org/05h0z7c09","country_code":"AE","type":"education","lineage":["https://openalex.org/I132806614"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sauleh Eetemadi","raw_affiliation_strings":["Department of Computer Science, University of Birmingham, Dubai, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Birmingham, Dubai, UAE","institution_ids":["https://openalex.org/I132806614"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5099853020"],"corresponding_institution_ids":["https://openalex.org/I67009956"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54575391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"743","last_page":"750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7232999801635742,"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":0.7232999801635742,"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/T13629","display_name":"Text Readability and Simplification","score":0.0560000017285347,"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":0.017500000074505806,"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/persian","display_name":"Persian","score":0.597599983215332},{"id":"https://openalex.org/keywords/formal-methods","display_name":"Formal methods","score":0.259799987077713},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.257099986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993999719619751},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.597599983215332},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40380001068115234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.086","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.086","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.086","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.086","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2111930270","https://openalex.org/W2948115951","https://openalex.org/W2963532001","https://openalex.org/W3172413486","https://openalex.org/W3188502483","https://openalex.org/W4239025696","https://openalex.org/W4410202262"],"related_works":[],"abstract_inverted_index":{"The":[0],"Formality":[1],"Style":[2],"Transformation":[3],"(FST)":[4],"task":[5],"aims":[6],"to":[7,21,45,103],"convert":[8],"informal":[9,79],"text":[10,81],"into":[11],"formal":[12,34,106],"while":[13],"preserving":[14],"the":[15,23,46,53,72],"original":[16],"meaning.":[17],"It":[18],"is":[19],"essential":[20],"improve":[22],"performance":[24,73],"of":[25,28,74,116],"a":[26,113],"variety":[27],"NLP":[29],"tasks":[30],"that":[31,57],"rely":[32],"on":[33],"language":[35],"input.":[36],"Nevertheless,":[37],"it":[38,99],"remains":[39],"challenging":[40],"for":[41,48,101,123],"low-resource":[42],"languages":[43,56],"due":[44],"need":[47],"high-quality":[49],"parallel":[50],"corpora.":[51],"On":[52],"other":[54],"hand,":[55],"use":[58],"non-Latin":[59],"scripts,":[60],"such":[61],"as":[62],"Persian":[63,80,124],"(Farsi),":[64],"are":[65],"morphologically":[66],"complex":[67],"and":[68,90,120,133],"underrepresented,":[69],"which":[70,97],"limits":[71],"pretrained":[75],"models.":[76],"More":[77],"specifically,":[78],"often":[82],"contains":[83],"colloquial":[84],"expressions,":[85],"dialectal":[86],"variations,":[87],"non-standard":[88],"spellings,":[89],"code-switching":[91],"with":[92],"English":[93],"or":[94],"Arabic":[95],"words,":[96],"makes":[98],"difficult":[100],"models":[102],"generate":[104],"accurate":[105],"equivalents.":[107],"In":[108],"this":[109,139],"survey,":[110],"we":[111,129],"provide":[112],"systematic":[114],"overview":[115],"existing":[117],"methods,":[118],"datasets,":[119],"evaluation":[121],"metrics":[122],"formality":[125],"style":[126],"transformation.":[127],"Finally,":[128],"discuss":[130],"open":[131],"challenges":[132],"identify":[134],"future":[135],"research":[136],"directions":[137],"in":[138],"domain.":[140]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-21T00:00:00"}