{"id":"https://openalex.org/W4416251704","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229319","title":"Towards Roman Urdu Named Entity Recognition: Standardized Dataset and Transformer-Based Approaches","display_name":"Towards Roman Urdu Named Entity Recognition: Standardized Dataset and Transformer-Based Approaches","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251704","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229319"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036312587","display_name":"Rafiul Haq","orcid":"https://orcid.org/0000-0002-7983-474X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rafiul Haq","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030524599","display_name":"Xiaowang Zhang","orcid":"https://orcid.org/0000-0002-3931-3886"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowang Zhang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009280810","display_name":"Sofonias Yitagesu","orcid":"https://orcid.org/0000-0002-9247-7521"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sofonias Yitagesu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029029867","display_name":"Wahab Khan","orcid":"https://orcid.org/0000-0002-5694-0419"},"institutions":[{"id":"https://openalex.org/I4210154218","display_name":"University of Science and Technology Bannu","ror":"https://ror.org/04be2dn15","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210154218"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Wahab Khan","raw_affiliation_strings":["University of Science and Technology,Department of Computer Science,Bannu,PK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology,Department of Computer Science,Bannu,PK","institution_ids":["https://openalex.org/I4210154218"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100736532","display_name":"Zhiyong Feng","orcid":"https://orcid.org/0000-0001-8158-7453"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Feng","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32495421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9182999730110168,"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":0.9182999730110168,"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":0.022600000724196434,"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":0.012000000104308128,"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/conditional-random-field","display_name":"Conditional random field","score":0.771399974822998},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.733299970626831},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6909000277519226},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5999000072479248},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4311000108718872},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.37540000677108765},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.771399974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.733299970626831},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6909000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204000115394592},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6061000227928162},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1989517911","https://openalex.org/W2064675550","https://openalex.org/W2409439155","https://openalex.org/W2949241676","https://openalex.org/W2961231993","https://openalex.org/W3035390927","https://openalex.org/W4200464847","https://openalex.org/W4225768509","https://openalex.org/W4283395836","https://openalex.org/W4321260730","https://openalex.org/W4385421470","https://openalex.org/W4391840625","https://openalex.org/W4399817145","https://openalex.org/W4400944325","https://openalex.org/W4402353307","https://openalex.org/W4403022777","https://openalex.org/W4403304337"],"related_works":[],"abstract_inverted_index":{"The":[0,43],"recent":[1],"progress":[2],"in":[3,25],"data":[4],"and":[5,18,38,54,65,109,145],"modeling":[6],"techniques":[7],"has":[8],"significantly":[9],"improved":[10],"Named":[11],"Entity":[12],"Recognition":[13],"(NER)":[14],"for":[15,47,94,133,142,148,165],"well-structured":[16],"texts":[17],"high-resource":[19],"languages.":[20],"However,":[21],"Roman":[22,48,82,187],"Urdu,":[23],"written":[24],"Latin":[26],"script,":[27],"poses":[28],"unique":[29],"challenges":[30],"due":[31],"to":[32,85,159,168],"its":[33],"informal":[34,64],"structure,":[35],"code-switching":[36],"tendencies,":[37],"lack":[39],"of":[40,182],"standardized":[41],"resources.":[42],"existing":[44],"NER":[45],"dataset":[46,84],"Urdu":[49,83,188],"suffers":[50],"from":[51],"inconsistent":[52],"annotations":[53],"undefined":[55],"entity":[56,95],"boundaries,":[57],"while":[58],"traditional":[59],"deep-learning":[60],"models":[61,104],"struggle":[62],"with":[63,122],"multilingual":[66,101],"text.":[67],"To":[68],"address":[69],"these":[70],"challenges,":[71],"this":[72],"study":[73],"makes":[74],"several":[75],"key":[76],"contributions.":[77],"First,":[78],"we":[79,99,112],"re-annotate":[80],"the":[81,90,161,171,185],"ensure":[86],"tagging":[87,92],"consistency,":[88],"adopting":[89],"BIOES":[91],"scheme":[93],"boundary":[96],"representation.":[97],"Second,":[98],"fine-tuned":[100],"pre-trained":[102],"language":[103],"(PLMs),":[105],"including":[106,126],"mBERT,":[107],"MuRIL,":[108],"XLM-R.":[110],"Finally,":[111],"introduce":[113],"XLM-R-IDCNN-BiLSTM-H,":[114],"a":[115,154],"novel":[116],"architecture":[117],"that":[118],"combines":[119],"transformer-based":[120],"embeddings":[121],"advanced":[123],"neural":[124],"components,":[125],"Iterated":[127],"Dilated":[128],"Convolutional":[129],"Neural":[130],"Networks":[131],"(IDCNN)":[132],"local":[134],"dependencies,":[135],"Bidirectional":[136],"Long":[137],"Short-Term":[138],"Memory":[139],"(BiLSTM)":[140],"networks":[141,147],"bidirectional":[143],"context,":[144],"highway":[146],"smooth":[149],"information":[150],"flow.":[151],"We":[152],"employ":[153],"conditional":[155],"random":[156],"field":[157],"(CRF)":[158],"obtain":[160],"optimal":[162],"tag":[163],"sequence":[164],"classification.":[166],"According":[167],"experimental":[169],"findings,":[170],"proposed":[172],"approach":[173],"delivers":[174],"state-of-the-art":[175],"performance,":[176],"which":[177],"yielded":[178],"an":[179],"F1":[180],"score":[181],"84.26%":[183],"on":[184],"re-annotated":[186],"dataset.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}