{"id":"https://openalex.org/W4401764370","doi":"https://doi.org/10.3390/computers13080212","title":"Investigating the Challenges and Opportunities in Persian Language Information Retrieval through Standardized Data Collections and Deep Learning","display_name":"Investigating the Challenges and Opportunities in Persian Language Information Retrieval through Standardized Data Collections and Deep Learning","publication_year":2024,"publication_date":"2024-08-21","ids":{"openalex":"https://openalex.org/W4401764370","doi":"https://doi.org/10.3390/computers13080212"},"language":"en","primary_location":{"id":"doi:10.3390/computers13080212","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13080212","pdf_url":"https://www.mdpi.com/2073-431X/13/8/212/pdf?version=1724232161","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/13/8/212/pdf?version=1724232161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106642453","display_name":"Sara Moniri","orcid":"https://orcid.org/0009-0007-0197-0630"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sara Moniri","raw_affiliation_strings":["Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany"],"raw_orcid":"https://orcid.org/0009-0007-0197-0630","affiliations":[{"raw_affiliation_string":"Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083970552","display_name":"Tobias Schlosser","orcid":"https://orcid.org/0000-0002-0682-4284"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Schlosser","raw_affiliation_strings":["Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0682-4284","affiliations":[{"raw_affiliation_string":"Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038259339","display_name":"Danny Kowerko","orcid":"https://orcid.org/0000-0002-4538-7814"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Danny Kowerko","raw_affiliation_strings":["Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4538-7814","affiliations":[{"raw_affiliation_string":"Junior Professorship of Media Computing, Chemnitz University of Technology, 09107 Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5106642453"],"corresponding_institution_ids":["https://openalex.org/I2610724"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.804,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86711477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"8","first_page":"212","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9878000020980835,"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":0.9056789875030518},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.6294881701469421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5502158403396606},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5049267411231995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5042537450790405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4809526801109314},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.364697128534317},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33839496970176697},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.20856702327728271},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.10085967183113098}],"concepts":[{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.9056789875030518},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.6294881701469421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5502158403396606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5049267411231995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5042537450790405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4809526801109314},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.364697128534317},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33839496970176697},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.20856702327728271},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.10085967183113098},{"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:10.3390/computers13080212","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13080212","pdf_url":"https://www.mdpi.com/2073-431X/13/8/212/pdf?version=1724232161","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a608817f8ef24bb1833a5480adef4f2b","is_oa":true,"landing_page_url":"https://doaj.org/article/a608817f8ef24bb1833a5480adef4f2b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Computers, Vol 13, Iss 8, p 212 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers13080212","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13080212","pdf_url":"https://www.mdpi.com/2073-431X/13/8/212/pdf?version=1724232161","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401764370.pdf","grobid_xml":"https://content.openalex.org/works/W4401764370.grobid-xml"},"referenced_works_count":104,"referenced_works":["https://openalex.org/W177754624","https://openalex.org/W317957491","https://openalex.org/W565003248","https://openalex.org/W1515688880","https://openalex.org/W1539361473","https://openalex.org/W1663984431","https://openalex.org/W1976124592","https://openalex.org/W1976713373","https://openalex.org/W1994616650","https://openalex.org/W2001642682","https://openalex.org/W2020172427","https://openalex.org/W2020278455","https://openalex.org/W2026306693","https://openalex.org/W2040713190","https://openalex.org/W2044565013","https://openalex.org/W2046325278","https://openalex.org/W2053154970","https://openalex.org/W2054003061","https://openalex.org/W2057256724","https://openalex.org/W2064675550","https://openalex.org/W2091944322","https://openalex.org/W2101098123","https://openalex.org/W2101105183","https://openalex.org/W2112796928","https://openalex.org/W2122111042","https://openalex.org/W2133552271","https://openalex.org/W2133669617","https://openalex.org/W2140485652","https://openalex.org/W2147800946","https://openalex.org/W2150102617","https://openalex.org/W2154579312","https://openalex.org/W2163539183","https://openalex.org/W2163605009","https://openalex.org/W2168012540","https://openalex.org/W2214534013","https://openalex.org/W2250539671","https://openalex.org/W2328364819","https://openalex.org/W2329524513","https://openalex.org/W2353267094","https://openalex.org/W2493916176","https://openalex.org/W2561466673","https://openalex.org/W2573062194","https://openalex.org/W2575537539","https://openalex.org/W2617241599","https://openalex.org/W2618179343","https://openalex.org/W2672337983","https://openalex.org/W2753628379","https://openalex.org/W2773044012","https://openalex.org/W2784240353","https://openalex.org/W2787894218","https://openalex.org/W2793350103","https://openalex.org/W2806934493","https://openalex.org/W2884001105","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2922493889","https://openalex.org/W2964252254","https://openalex.org/W2964584413","https://openalex.org/W3006229125","https://openalex.org/W3019166713","https://openalex.org/W3019284033","https://openalex.org/W3030384960","https://openalex.org/W3032299950","https://openalex.org/W3098613831","https://openalex.org/W3119163485","https://openalex.org/W3131788760","https://openalex.org/W3131997754","https://openalex.org/W3160170194","https://openalex.org/W3191950921","https://openalex.org/W3208602520","https://openalex.org/W3213458975","https://openalex.org/W3217441761","https://openalex.org/W4205499037","https://openalex.org/W4206192903","https://openalex.org/W4206775476","https://openalex.org/W4235743066","https://openalex.org/W4236845853","https://openalex.org/W4237783107","https://openalex.org/W4239510810","https://openalex.org/W4281621698","https://openalex.org/W4288716088","https://openalex.org/W4306955484","https://openalex.org/W4309224964","https://openalex.org/W4309788759","https://openalex.org/W4310813909","https://openalex.org/W4313585449","https://openalex.org/W4378603593","https://openalex.org/W4386566324","https://openalex.org/W4389524246","https://openalex.org/W4389762644","https://openalex.org/W4394625882","https://openalex.org/W4402798551","https://openalex.org/W6637623960","https://openalex.org/W6658331526","https://openalex.org/W6676070474","https://openalex.org/W6679149589","https://openalex.org/W6680994997","https://openalex.org/W6681875376","https://openalex.org/W6739901393","https://openalex.org/W6751896580","https://openalex.org/W6766302142","https://openalex.org/W6776085753","https://openalex.org/W6777410595","https://openalex.org/W6834106623"],"related_works":["https://openalex.org/W2359053655","https://openalex.org/W2387777532","https://openalex.org/W2382709029","https://openalex.org/W2389147080","https://openalex.org/W2377883125","https://openalex.org/W2362479786","https://openalex.org/W2392455911","https://openalex.org/W2374248756","https://openalex.org/W2375492428","https://openalex.org/W2350419982"],"abstract_inverted_index":{"The":[0],"Persian":[1,49,93,112],"language,":[2],"also":[3],"known":[4],"as":[5,126],"Farsi,":[6],"is":[7,57],"distinguished":[8],"by":[9],"its":[10,43,145],"intricate":[11],"morphological":[12],"richness,":[13],"yet":[14],"it":[15,29],"contends":[16],"with":[17],"a":[18,105,141],"paucity":[19],"of":[20,63,71,84,111,138],"linguistic":[21],"resources.":[22],"With":[23],"an":[24,149],"estimated":[25],"110":[26],"million":[27],"speakers,":[28],"finds":[30],"prevalence":[31],"across":[32],"Iran,":[33],"Tajikistan,":[34],"Uzbekistan,":[35],"Iraq,":[36],"Russia,":[37],"Azerbaijan,":[38],"and":[39,100,114],"Afghanistan.":[40],"However,":[41],"despite":[42],"widespread":[44],"usage,":[45],"scholarly":[46],"investigations":[47,134],"into":[48],"document":[50],"retrieval":[51],"remain":[52],"notably":[53],"scarce.":[54],"This":[55],"circumstance":[56],"primarily":[58],"attributed":[59],"to":[60,96],"the":[61,69,82,109,136],"absence":[62],"standardized":[64],"test":[65],"collections,":[66],"which":[67,118],"impedes":[68],"advancement":[70],"comprehensive":[72],"research":[73],"endeavors":[74],"within":[75],"this":[76,89],"realm.":[77],"As":[78],"data":[79],"corpora":[80],"are":[81,130],"foundation":[83],"natural":[85],"language":[86,94],"processing":[87,110],"applications,":[88],"work":[90],"aims":[91],"at":[92],"datasets":[95],"address":[97],"their":[98,115],"availability":[99],"structure.":[101],"Subsequently,":[102],"we":[103],"motivate":[104],"learning-based":[106],"framework":[107],"for":[108,117,148],"texts":[113],"recognition,":[116],"current":[119],"state-of-the-art":[120],"approaches":[121],"from":[122],"deep":[123,127],"learning,":[124],"such":[125,140],"neural":[128],"networks,":[129],"further":[131],"discussed.":[132],"Our":[133],"highlight":[135],"challenges":[137],"realizing":[139],"system":[142],"while":[143],"emphasizing":[144],"possible":[146],"benefits":[147],"otherwise":[150],"rarely":[151],"covered":[152],"language.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}