{"id":"https://openalex.org/W4403459086","doi":"https://doi.org/10.1007/s10772-024-10136-2","title":"A transformer-based approach to Nigerian Pidgin text generation","display_name":"A transformer-based approach to Nigerian Pidgin text generation","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403459086","doi":"https://doi.org/10.1007/s10772-024-10136-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-024-10136-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10136-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10136-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10136-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114291823","display_name":"Kabir Garba","orcid":null},"institutions":[{"id":"https://openalex.org/I2800190170","display_name":"Federal University Lokoja","ror":"https://ror.org/018ced875","country_code":"NG","type":"education","lineage":["https://openalex.org/I2800190170"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Kabir Garba","raw_affiliation_strings":["Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria","institution_ids":["https://openalex.org/I2800190170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059796848","display_name":"Taiwo Kolajo","orcid":"https://orcid.org/0000-0001-6780-2495"},"institutions":[{"id":"https://openalex.org/I2800190170","display_name":"Federal University Lokoja","ror":"https://ror.org/018ced875","country_code":"NG","type":"education","lineage":["https://openalex.org/I2800190170"]},{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["NG","ZA"],"is_corresponding":true,"raw_author_name":"Taiwo Kolajo","raw_affiliation_strings":["Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria","Department of Informatics, Faculty of Engineering, Built Environment & IT, University of Pretoria, Pretoria, Republic of South Africa (RSA)"],"raw_orcid":"https://orcid.org/0000-0001-6780-2495","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria","institution_ids":["https://openalex.org/I2800190170"]},{"raw_affiliation_string":"Department of Informatics, Faculty of Engineering, Built Environment & IT, University of Pretoria, Pretoria, Republic of South Africa (RSA)","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062810908","display_name":"Joshua Babatunde Agbogun","orcid":null},"institutions":[{"id":"https://openalex.org/I2800190170","display_name":"Federal University Lokoja","ror":"https://ror.org/018ced875","country_code":"NG","type":"education","lineage":["https://openalex.org/I2800190170"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Joshua B. Agbogun","raw_affiliation_strings":["Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University Lokoja, P.M.B 1154, Lokoja, Kogi State, Nigeria","institution_ids":["https://openalex.org/I2800190170"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059796848"],"corresponding_institution_ids":["https://openalex.org/I2800190170","https://openalex.org/I69552723"],"apc_list":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":{"value":2780,"currency":"USD","value_usd":2780},"fwci":0.972,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79821441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":"4","first_page":"1027","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9905999898910522,"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":0.9905999898910522,"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":0.9886999726295471,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8597970008850098},{"id":"https://openalex.org/keywords/pidgin","display_name":"Pidgin","score":0.8051440119743347},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6699407696723938},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.46186691522598267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43175429105758667},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20641747117042542},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12965795397758484},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06387022137641907},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04553636908531189}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597970008850098},{"id":"https://openalex.org/C2776545096","wikidata":"https://www.wikidata.org/wiki/Q33831","display_name":"Pidgin","level":3,"score":0.8051440119743347},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6699407696723938},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.46186691522598267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43175429105758667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20641747117042542},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12965795397758484},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06387022137641907},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04553636908531189},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C174613046","wikidata":"https://www.wikidata.org/wiki/Q33289","display_name":"Creole language","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10772-024-10136-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10136-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10136-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},{"id":"pmh:oai:repository.up.ac.za:2263/101508","is_oa":true,"landing_page_url":"http://hdl.handle.net/2263/101508","pdf_url":"https://repository.up.ac.za/bitstreams/aa7b00fd-f0f9-4cc7-87e2-d418b6c6b317/download","source":{"id":"https://openalex.org/S4306401870","display_name":"UpSpace Institutional Repository (University of Pretoria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I69552723","host_organization_name":"University of Pretoria","host_organization_lineage":["https://openalex.org/I69552723"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10772-024-10136-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10136-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10136-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320692","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403459086.pdf","grobid_xml":"https://content.openalex.org/works/W4403459086.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1487542866","https://openalex.org/W2944931850","https://openalex.org/W2949526700","https://openalex.org/W3011506747","https://openalex.org/W3016399951","https://openalex.org/W3039777472","https://openalex.org/W3092288641","https://openalex.org/W3099695344","https://openalex.org/W3121250149","https://openalex.org/W3130890978","https://openalex.org/W3138794547","https://openalex.org/W3153266325","https://openalex.org/W3213418658","https://openalex.org/W4226031686","https://openalex.org/W4229030698","https://openalex.org/W4285060468","https://openalex.org/W4321094913","https://openalex.org/W4381572755","https://openalex.org/W4385284981","https://openalex.org/W4385416665","https://openalex.org/W4386290290","https://openalex.org/W4391540147","https://openalex.org/W4392560653","https://openalex.org/W4393853326","https://openalex.org/W6761451552"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2978083540","https://openalex.org/W2411155294","https://openalex.org/W2147750988","https://openalex.org/W2056722378","https://openalex.org/W3119137589","https://openalex.org/W4313307225","https://openalex.org/W3206132041","https://openalex.org/W4362570934"],"abstract_inverted_index":{"Abstract":[0],"This":[1,80,104,199],"paper":[2,81],"describes":[3],"the":[4,54,89,107,113,135,143,157,201,207,211,218,277,287,299,313],"development":[5],"of":[6,91,134,150,171,186,203,258],"a":[7,19,61,76,97,120,131,147,255,261,305],"transformer-based":[8,279],"text":[9,38,98,137,182,205,213,294],"generation":[10,39,99,317],"model":[11,100,118,158,281],"for":[12,63,101,173,180,188,194,234,241,273,290,308],"Nigerian":[13,29,64,102,162,251,292,314],"Pidgin":[14,30,163,252,293,315],"also":[15],"known":[16],"as":[17,248,304],"Naij\u00e1,":[18],"popular":[20],"language":[21,42,274,280,316],"in":[22,34,71,312],"West":[23],"Africa.":[24],"Despite":[25,142],"its":[26],"wide":[27],"use,":[28],"remains":[31],"under-resourced,":[32],"particularly":[33],"areas":[35],"related":[36],"to":[37,49,83,95,111],"and":[40,74,127,139,178,192,206,282,310,318],"natural":[41],"processing.":[43],"These":[44],"difficulties":[45,144],"are":[46,236,271],"primarily":[47],"due":[48],"technological":[50],"constraints":[51],"rather":[52],"than":[53,239],"language\u2019s":[55],"fundamental":[56],"attributes.":[57],"There":[58],"is":[59,69,215],"currently":[60],"demand":[62],"Pidgin-specific":[65],"solutions":[66],"because":[67],"it":[68],"used":[70],"everyday":[72],"communication":[73],"has":[75],"unique":[77],"linguistic":[78],"blend.":[79],"aims":[82],"close":[84],"this":[85],"gap":[86],"by":[87,146],"exploring":[88],"application":[90],"state-of-the-art":[92],"transformer":[93],"technology":[94],"develop":[96],"Pidgin.":[103],"work":[105,222,301],"uses":[106],"public":[108],"Afriberta-corpus":[109],"dataset":[110],"optimize":[112],"Generative":[114],"Pre-trained":[115],"Transformer":[116],"(GPT-2)":[117],"across":[119],"sizeable":[121],"dataset.":[122],"The":[123,165],"performance":[124,166],"evaluators,":[125],"BLEU":[126,184,232,246,256],"Perplexity":[128],"metrics":[129],"provide":[130],"detailed":[132],"breakdown":[133],"model\u2019s":[136,288],"quality":[138,202],"predictive":[140],"accuracy.":[141],"caused":[145],"limited":[148],"amount":[149],"training":[151],"data,":[152],"preliminary":[153],"evaluations":[154],"show":[155],"that":[156,231,268],"can":[159,302],"generate":[160],"coherent":[161,291],"text.":[164],"evaluation":[167,283],"yielded":[168],"perplexity":[169],"scores":[170,185,233],"43.56":[172],"variable":[174,195],"target":[175,197],"reference":[176,196,219],"length":[177,191,214],"43.26":[179],"fixed":[181,189],"length.":[183,198],"0.15":[187],"max":[190],"0.56":[193],"highlights":[200],"generated":[204,212],"significant":[208],"improvement":[209],"when":[210],"aligned":[216],"with":[217,245,254],"target.":[220],"Our":[221,250],"was":[223],"benchmarked":[224],"against":[225],"African":[226],"American":[227,243],"Vernacular":[228],"(AAVE)":[229],"revealing":[230],"AAVE":[235],"significantly":[237],"lower":[238],"those":[240],"Standard":[242],"English,":[244],"given":[247],"0.26.":[249],"model,":[253],"score":[257],"0.56,":[259],"shows":[260],"better":[262],"performance.":[263],"However,":[264],"both":[265,269],"results":[266],"suggest":[267],"dialects":[270],"challenging":[272],"models.":[275],"Leveraging":[276],"pre-trained":[278],"metrics,":[284],"we":[285],"showcase":[286],"capacity":[289],"generation.":[295],"For":[296],"future":[297],"research,":[298],"research":[300],"serve":[303],"good":[306],"foundation":[307],"advancement":[309],"progress":[311],"other":[319],"low-resource":[320],"languages.":[321]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}