{"id":"https://openalex.org/W4391840625","doi":"https://doi.org/10.1145/3648362","title":"Enriching Urdu NER with BERT Embedding, Data Augmentation, and Hybrid Encoder-CNN Architecture","display_name":"Enriching Urdu NER with BERT Embedding, Data Augmentation, and Hybrid Encoder-CNN Architecture","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391840625","doi":"https://doi.org/10.1145/3648362"},"language":"en","primary_location":{"id":"doi:10.1145/3648362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648362","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5035452139","display_name":"Anil Ahmed","orcid":"https://orcid.org/0000-0001-6223-875X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anil Ahmed","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6223-875X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Degen Huang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8860-7805","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016754576","display_name":"Syed Yasser Arafat","orcid":"https://orcid.org/0000-0002-2121-1865"},"institutions":[{"id":"https://openalex.org/I69716792","display_name":"Mirpur University of Science and Technology","ror":"https://ror.org/04qjkhc08","country_code":"PK","type":"education","lineage":["https://openalex.org/I69716792"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Syed Yasser Arafat","raw_affiliation_strings":["Mirpur University of Science and Technology, Mirpur, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-2121-1865","affiliations":[{"raw_affiliation_string":"Mirpur University of Science and Technology, Mirpur, Pakistan","institution_ids":["https://openalex.org/I69716792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103011352","display_name":"Imran Hameed .","orcid":"https://orcid.org/0009-0006-4148-5755"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Imran Hameed","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0006-4148-5755","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4455,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.94935302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"4","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9955000281333923,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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/architecture","display_name":"Architecture","score":0.603590726852417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6024428606033325},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5323531627655029},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.5253190994262695},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46242019534111023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3599444031715393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32437941431999207},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.19337204098701477},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07929450273513794},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.05908331274986267}],"concepts":[{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.603590726852417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6024428606033325},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5323531627655029},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.5253190994262695},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46242019534111023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3599444031715393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32437941431999207},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.19337204098701477},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07929450273513794},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.05908331274986267},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3648362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648362","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5630136037","display_name":null,"funder_award_id":"2020AAA0108004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1993784968","https://openalex.org/W2054460891","https://openalex.org/W2136939460","https://openalex.org/W2142384583","https://openalex.org/W2143612262","https://openalex.org/W2189055190","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2736989307","https://openalex.org/W2740887992","https://openalex.org/W2756253150","https://openalex.org/W2787560479","https://openalex.org/W2791193613","https://openalex.org/W2896457183","https://openalex.org/W2897098357","https://openalex.org/W2911285049","https://openalex.org/W2912145841","https://openalex.org/W2912310990","https://openalex.org/W2919115771","https://openalex.org/W2949241676","https://openalex.org/W2961231993","https://openalex.org/W2965373594","https://openalex.org/W2975059944","https://openalex.org/W2981040094","https://openalex.org/W2996428491","https://openalex.org/W3006948250","https://openalex.org/W3010293452","https://openalex.org/W3039049049","https://openalex.org/W3040074533","https://openalex.org/W3049412671","https://openalex.org/W3115908473","https://openalex.org/W3185093489","https://openalex.org/W3213591530","https://openalex.org/W4205476602","https://openalex.org/W4206437118","https://openalex.org/W4206660322","https://openalex.org/W4225768509","https://openalex.org/W4282939402","https://openalex.org/W4283395836","https://openalex.org/W4287746114","https://openalex.org/W4287829148","https://openalex.org/W4292779060","https://openalex.org/W4301581299","https://openalex.org/W4302617179","https://openalex.org/W4306680578","https://openalex.org/W4312802027","https://openalex.org/W4312925950","https://openalex.org/W4321784420","https://openalex.org/W4327748029","https://openalex.org/W4368371908","https://openalex.org/W4385245566","https://openalex.org/W4385572519","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6680230698","https://openalex.org/W6739901393","https://openalex.org/W6758325387","https://openalex.org/W6767440493","https://openalex.org/W6773820404","https://openalex.org/W6778883912","https://openalex.org/W6997437372"],"related_works":["https://openalex.org/W1588484110","https://openalex.org/W1566901819","https://openalex.org/W604003083","https://openalex.org/W597280011","https://openalex.org/W4310798948","https://openalex.org/W642060233","https://openalex.org/W4389314469","https://openalex.org/W4390236247","https://openalex.org/W2083227284","https://openalex.org/W1601953538"],"abstract_inverted_index":{"Named":[0,84,142],"Entity":[1,85],"Recognition":[2,86],"(NER)":[3],"is":[4,120],"an":[5,215],"indispensable":[6],"component":[7],"of":[8,61,72,185,223],"Natural":[9],"Language":[10],"Processing":[11],"(NLP),":[12],"which":[13],"aims":[14],"to":[15,153,180,192],"identify":[16],"and":[17,39,69,88,111,125,130,197,200,214],"classify":[18],"entities":[19],"within":[20],"text":[21],"data.":[22,74],"While":[23],"Deep":[24],"Learning":[25],"(DL)":[26],"models":[27,115,152],"have":[28],"excelled":[29],"in":[30],"NER":[31],"for":[32,228],"well-resourced":[33],"languages":[34,49],"such":[35,50],"as":[36,51],"English,":[37],"Spanish,":[38],"Chinese,":[40],"they":[41],"face":[42],"significant":[43],"hurdles":[44],"when":[45],"dealing":[46],"with":[47,145,174],"low-resource":[48],"Urdu.":[52,186],"These":[53,187],"challenges":[54],"stem":[55],"from":[56,108,113],"the":[57,70,159,163,182,190,208,220,229],"intricate":[58,183],"linguistic":[59],"characteristics":[60],"Urdu,":[62],"including":[63],"morphological":[64],"diversity,":[65],"a":[66,134,166,171,175],"context-dependent":[67],"lexicon,":[68],"scarcity":[71],"training":[73,160],"This":[75],"study":[76,164],"addresses":[77],"these":[78],"issues":[79],"by":[80],"focusing":[81],"on":[82,122],"Urdu":[83,128],"(U-NER)":[87],"introducing":[89],"three":[90],"key":[91],"contributions.":[92],"First,":[93],"various":[94],"pre-trained":[95,149],"embedding":[96],"methods":[97],"are":[98],"employed,":[99],"encompassing":[100],"Word2vec":[101],"(W2V),":[102],"GloVe,":[103],"FastText,":[104],"Bidirectional":[105],"Encoder":[106,173],"Representations":[107],"Transformers":[109],"(BERT),":[110],"Embeddings":[112],"language":[114,151],"(ELMo).":[116],"In":[117],"particular,":[118],"fine-tuning":[119],"performed":[121],"BERT":[123,212],"BASE":[124],"ELMo":[126],"using":[127],"Wikipedia":[129],"news":[131],"articles.":[132],"Second,":[133],"novel":[135,167],"generative":[136],"Data":[137],"Augmentation":[138],"(DA)":[139],"technique":[140],"replaces":[141],"Entities":[143],"(NEs)":[144],"mask":[146],"tokens,":[147,156],"employing":[148],"masked":[150,155],"predict":[154],"effectively":[157],"expanding":[158],"dataset.":[161],"Finally,":[162],"introduces":[165],"hybrid":[168],"model":[169,191],"combining":[170],"Transformer":[172],"Convolutional":[176],"Neural":[177],"Network":[178],"(CNN)":[179],"capture":[181],"morphology":[184],"modules":[188],"enable":[189],"handle":[193],"polysemy,":[194],"extract":[195],"short-":[196],"long-range":[198],"dependencies,":[199],"enhance":[201],"learning":[202],"capacity.":[203],"Empirical":[204],"experiments":[205],"demonstrate":[206],"that":[207],"proposed":[209],"model,":[210],"incorporating":[211],"embeddings":[213],"innovative":[216],"DA":[217],"approach,":[218],"attains":[219],"highest":[221],"F1-score":[222],"93.99%,":[224],"highlighting":[225],"its":[226],"efficacy":[227],"U-NER":[230],"task.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}