{"id":"https://openalex.org/W4368371908","doi":"https://doi.org/10.1145/3595861","title":"Using Data Augmentation and Bidirectional Encoder Representations from Transformers for Improving Punjabi Named Entity Recognition","display_name":"Using Data Augmentation and Bidirectional Encoder Representations from Transformers for Improving Punjabi Named Entity Recognition","publication_year":2023,"publication_date":"2023-05-04","ids":{"openalex":"https://openalex.org/W4368371908","doi":"https://doi.org/10.1145/3595861"},"language":"en","primary_location":{"id":"doi:10.1145/3595861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3595861","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/A5085961010","display_name":"Hamza Khalid","orcid":"https://orcid.org/0000-0003-4097-0178"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Hamza Khalid","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-4097-0178","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044013451","display_name":"Ghulam Murtaza","orcid":"https://orcid.org/0000-0002-9205-6356"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ghulam Murtaza","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-9205-6356","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102988896","display_name":"Qaiser Abbas","orcid":"https://orcid.org/0000-0001-9246-5208"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Qaiser Abbas","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan"],"raw_orcid":"https://orcid.org/0000-0001-9246-5208","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Punjab, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142732210"],"apc_list":null,"apc_paid":null,"fwci":1.5863,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85491307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.9396713972091675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8434158563613892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7153962254524231},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6785404086112976},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.674981951713562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888136029243469},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5101728439331055},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4957347810268402},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4905697703361511},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.06725320219993591}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.9396713972091675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434158563613892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7153962254524231},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6785404086112976},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.674981951713562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888136029243469},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5101728439331055},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4957347810268402},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4905697703361511},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.06725320219993591},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3595861","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1593502373","https://openalex.org/W2183106148","https://openalex.org/W2295000399","https://openalex.org/W2409439155","https://openalex.org/W2442408233","https://openalex.org/W2528773445","https://openalex.org/W2756253150","https://openalex.org/W2758692100","https://openalex.org/W2766140847","https://openalex.org/W2896457183","https://openalex.org/W2912145841","https://openalex.org/W2949241676","https://openalex.org/W2950813464","https://openalex.org/W2961231993","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2974875810","https://openalex.org/W2975059944","https://openalex.org/W2996428491","https://openalex.org/W3007799408","https://openalex.org/W3011411500","https://openalex.org/W3017222382","https://openalex.org/W3094176124","https://openalex.org/W3105966348","https://openalex.org/W3115908473","https://openalex.org/W3140747828","https://openalex.org/W3159597830","https://openalex.org/W3173162544","https://openalex.org/W3174068771","https://openalex.org/W3180181113","https://openalex.org/W3201304893","https://openalex.org/W4200068734","https://openalex.org/W4206437118","https://openalex.org/W4283395836","https://openalex.org/W4285100132","https://openalex.org/W4289638072","https://openalex.org/W4292779060","https://openalex.org/W6778883912","https://openalex.org/W6798060926","https://openalex.org/W6807067365","https://openalex.org/W7067687685"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W2883921205","https://openalex.org/W4313162113","https://openalex.org/W1884363728","https://openalex.org/W3133906981"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition":[2],"(NER)":[3],"is":[4,53,65],"a":[5,66,125,158,181],"task":[6],"of":[7,60,69,128],"proper":[8],"noun":[9],"identification":[10],"from":[11,166],"natural":[12,32],"language":[13,33],"text":[14],"and":[15,24,40,139,183],"classification":[16],"into":[17],"various":[18,74],"types":[19],"such":[20],"as":[21,162],"location,":[22],"person,":[23],"organization.":[25],"Due":[26],"to":[27,57],"NER's":[28],"applications":[29],"in":[30,90,109],"different":[31],"processing":[34],"(NLP)":[35],"tasks,":[36],"numerous":[37],"NER":[38,48,92,104,121,171],"approaches":[39],"benchmark":[41],"datasets":[42],"have":[43,76],"been":[44],"proposed.":[45],"However,":[46],"developing":[47,91],"techniques":[49],"for":[50,93,102,105,169],"low-resource":[51],"languages":[52],"still":[54],"limited":[55],"due":[56],"the":[58,83,88,94,106,115,149,153,170,177],"absence":[59],"substantial":[61],"training":[62],"datasets.":[63],"Punjabi":[64,103],"classic":[67],"example":[68],"low":[70],"resource":[71],"language.":[72],"Although":[73],"researchers":[75],"worked":[77],"on":[78,82,180],"Punjabi,":[79],"they":[80],"focused":[81],"Gurmukhi":[84],"script.":[85],"To":[86],"overcome":[87],"challenges":[89],"Shahmukhi":[95,107],"script,":[96],"we":[97,156],"present":[98],"an":[99],"improved":[100],"technique":[101],"script":[108],"this":[110],"paper.":[111],"We":[112,173],"firstly":[113],"extend":[114],"existing":[116],"dataset":[117,135,185],"by":[118,123],"adding":[119],"new":[120,182],"classes":[122],"leveraging":[124],"novel":[126],"Pool":[127],"Words":[129],"data":[130],"augmentation":[131],"strategy.":[132],"Our":[133],"extended":[134],"has":[136],"11,31,509":[137],"tokens":[138],"1,25,789":[140],"labeled":[141],"entities":[142,146],"with":[143],"more":[144],"named":[145],"(NEs)":[147],"than":[148],"older":[150,184],"dataset.":[151],"In":[152],"next":[154],"step,":[155],"fine-tuned":[157],"transformer":[159],"model":[160],"known":[161],"Bidirectional":[163],"Encoder":[164],"Representations":[165],"Transformers":[167],"(BERT)":[168],"task.":[172],"performed":[174],"experiments":[175],"using":[176],"proposed":[178],"approach":[179],"version,":[186],"showing":[187],"that":[188],"our":[189],"method":[190],"achieved":[191],"competitive":[192],"results.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}