{"id":"https://openalex.org/W3188502483","doi":"https://doi.org/10.1145/3468691.3468710","title":"Informal-to-Formal Word Conversion for Persian Language Using Natural Language Processing Techniques","display_name":"Informal-to-Formal Word Conversion for Persian Language Using Natural Language Processing Techniques","publication_year":2021,"publication_date":"2021-05-20","ids":{"openalex":"https://openalex.org/W3188502483","doi":"https://doi.org/10.1145/3468691.3468710","mag":"3188502483"},"language":"en","primary_location":{"id":"doi:10.1145/3468691.3468710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468691.3468710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd International Conference on Computing, Networks and Internet of Things (CNIOT 2021)","raw_type":"proceedings-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/A5011099715","display_name":"Amin Naemi","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Amin Naemi","raw_affiliation_strings":["University of Southern Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019647401","display_name":"Marjan Mansourvar","orcid":"https://orcid.org/0000-0001-6492-7858"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Marjan Mansourvar","raw_affiliation_strings":["University of Southern Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025581947","display_name":"Mostafa Naemi","orcid":"https://orcid.org/0000-0003-3343-6655"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mostafa Naemi","raw_affiliation_strings":["The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048702963","display_name":"Bahman Damirchilu","orcid":null},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Bahman Damirchilu","raw_affiliation_strings":["Amirkabir University of Technology (Tehran Polytechnic), Iran"],"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology (Tehran Polytechnic), Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071114884","display_name":"Ali Ebrahimi","orcid":"https://orcid.org/0000-0002-3332-6205"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ali Ebrahimi","raw_affiliation_strings":["University of Southern Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089302640","display_name":"Uffe Kock Wiil","orcid":"https://orcid.org/0000-0001-6898-4083"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Uffe Kock Wiil","raw_affiliation_strings":["University of Southern Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Denmark","institution_ids":["https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011099715"],"corresponding_institution_ids":["https://openalex.org/I177969490"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55094542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9839000105857849,"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":0.800101637840271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6783105134963989},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5339927077293396},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5293496251106262},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.5235692858695984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4985930919647217},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.44241276383399963},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.4389636814594269},{"id":"https://openalex.org/keywords/formal-language","display_name":"Formal language","score":0.4239475131034851},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3708128333091736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2682804465293884},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.13256019353866577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800101637840271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6783105134963989},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5339927077293396},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5293496251106262},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.5235692858695984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4985930919647217},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.44241276383399963},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.4389636814594269},{"id":"https://openalex.org/C146072743","wikidata":"https://www.wikidata.org/wiki/Q192161","display_name":"Formal language","level":2,"score":0.4239475131034851},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3708128333091736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2682804465293884},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.13256019353866577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3468691.3468710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468691.3468710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd International Conference on Computing, Networks and Internet of Things (CNIOT 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/6e84a506-a5b7-45d3-98ca-e48167caaea7","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/6e84a506-a5b7-45d3-98ca-e48167caaea7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Naemi, A, Mansourvar, M, Naemi, M, Damirchilu, B, Ebrahimi, A & Kock Wiil, U 2021, Informal-to-formal word conversion for persian language using natural language processing techniques. in Proceedings of 2021 2nd International Conference on Computing, Networks and Internet of Things., 19, Association for Computing Machinery, 2nd International Conference on Computing, Networks and Internet of Things, CNIOT 2021, Beijing, China, 20/05/2021. https://doi.org/10.1145/3468691.3468710","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1486212465","https://openalex.org/W1494632860","https://openalex.org/W1550267443","https://openalex.org/W2010595692","https://openalex.org/W2021092958","https://openalex.org/W2078591799","https://openalex.org/W2172281621","https://openalex.org/W2480353959","https://openalex.org/W2536985167","https://openalex.org/W2777111309","https://openalex.org/W2948115951","https://openalex.org/W2982514750"],"related_works":["https://openalex.org/W2913520953","https://openalex.org/W4310801723","https://openalex.org/W2383292628","https://openalex.org/W2067569787","https://openalex.org/W2401646948","https://openalex.org/W226586525","https://openalex.org/W2362145681","https://openalex.org/W2413973858","https://openalex.org/W2079798264","https://openalex.org/W2551652406"],"abstract_inverted_index":{"A":[0],"vast":[1],"amount":[2],"of":[3,17,35,46,61,107,149,178,189,215,231],"text":[4],"data":[5,27],"is":[6,235],"available":[7],"today":[8],"on":[9,58,104],"the":[10,14,33,43,59,70,86,105,112,120,142,160,179,184,190,197,200,219,228,232],"Internet":[11],"due":[12,41],"to":[13,42,52,65,110,119,124,135,140,186],"extensive":[15],"use":[16],"social":[18],"media.":[19],"Valuable":[20],"information":[21,36],"can":[22,38,174],"be":[23,39],"extracted":[24,84,158],"from":[25,85,159],"this":[26,54,74],"through":[28,155],"natural":[29],"language":[30],"processing.":[31],"However,":[32],"process":[34],"extraction":[37],"difficult":[40],"informal":[44,63,81,96,181],"forms":[45,122],"these":[47],"texts.":[48],"This":[49],"paper":[50],"aims":[51],"address":[53],"challenge":[55],"by":[56,68],"focusing":[57],"conversion":[60,151],"Persian":[62,95,164,180,206],"words":[64,67,82,97],"formal":[66,79,113,121,144,193],"using":[69],"spell-checking":[71],"approach.":[72],"For":[73],"purpose,":[75],"two":[76,204],"datasets":[77],"for":[78],"and":[80,203,209,217],"were":[83,98,116,133],"four":[87,161],"most":[88,162],"visited":[89,163],"news":[90,166],"websites":[91],"in":[92,213],"Persian.":[93],"Then":[94],"divided":[99],"into":[100],"multiple":[101],"categories":[102],"based":[103],"level":[106],"changes":[108],"required":[109],"build":[111],"equivalents.":[114,146],"These":[115],"then":[117],"converted":[118],"according":[123],"their":[125],"features.":[126],"Statistical":[127],"analyses":[128],"combined":[129],"with":[130,183],"correction":[131],"rules":[132],"used":[134],"produce":[136],"a":[137],"\u201ccandidate":[138],"list\u201d":[139],"find":[141],"best":[143,191],"candidate":[145],"The":[147],"performance":[148],"our":[150,171],"system":[152,173,202,221,234],"was":[153],"evaluated":[154],"people's":[156],"comments":[157],"(Farsi)":[165],"agencies.":[167],"Results":[168],"show":[169],"that":[170,212,227],"proposed":[172,201,220,233],"detect":[175,187],"approximately":[176],"94%":[177],"words,":[182],"ability":[185],"85%":[188],"equivalent":[192],"words.":[194],"In":[195],"addition,":[196],"comparison":[198],"between":[199],"well-known":[205],"spell-checkers,":[207],"Virastyar":[208],"Vafa,":[210],"shows":[211,226],"terms":[214],"detection":[216],"correction,":[218],"outperforms":[222],"significantly.":[223],"Further":[224],"analysis":[225],"time":[229],"complexity":[230],"linear.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}