{"id":"https://openalex.org/W4398588453","doi":"https://doi.org/10.7910/dvn/6n5v1k","title":"Kencorpus: Kenyan Languages Corpus","display_name":"Kencorpus: Kenyan Languages Corpus","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4398588453","doi":"https://doi.org/10.7910/dvn/6n5v1k"},"language":"en","primary_location":{"id":"doi:10.7910/dvn/6n5v1k","doi":"https://doi.org/10.7910/dvn/6n5v1k","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/6n5v1k","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7910/dvn/6n5v1k","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014764462","display_name":"Barack Wanjawa","orcid":"https://orcid.org/0000-0003-0198-3179","observed_orcids":["https://orcid.org/0000-0003-0198-3179"]},"institutions":[{"id":"https://openalex.org/I12859529","display_name":"University of Nairobi","ror":"https://ror.org/02y9nww90","country_code":"KE","type":"education","lineage":["https://openalex.org/I12859529"]},{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Wanjawa, Barack","raw_affiliation_strings":["University of Nairobi","(Maseno University)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nairobi","institution_ids":["https://openalex.org/I12859529"]},{"raw_affiliation_string":"(Maseno University)","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanzare, Lilian D.A.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Wanzare, Lilian D.A.","raw_affiliation_strings":["Maseno University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maseno University","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068463664","display_name":"Florence Indede","orcid":"https://orcid.org/0000-0003-4285-770X","observed_orcids":["https://orcid.org/0000-0003-4285-770X"]},"institutions":[{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Indede, Florence","raw_affiliation_strings":["Maseno University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maseno University","institution_ids":["https://openalex.org/I195610458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045469425","display_name":"Owen McOnyango","orcid":"https://orcid.org/0000-0002-1276-0395","observed_orcids":["https://orcid.org/0000-0002-1276-0395"]},"institutions":[{"id":"https://openalex.org/I12859529","display_name":"University of Nairobi","ror":"https://ror.org/02y9nww90","country_code":"KE","type":"education","lineage":["https://openalex.org/I12859529"]},{"id":"https://openalex.org/I195610458","display_name":"Maseno University","ror":"https://ror.org/023pskh72","country_code":"KE","type":"education","lineage":["https://openalex.org/I195610458"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"McOnyango, Owen","raw_affiliation_strings":["Maseno University","(University of Nairobi)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maseno University","institution_ids":["https://openalex.org/I195610458"]},{"raw_affiliation_string":"(University of Nairobi)","institution_ids":["https://openalex.org/I12859529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071646145","display_name":"Edward Ombui","orcid":"https://orcid.org/0000-0002-1787-0681","observed_orcids":["https://orcid.org/0000-0002-1787-0681"]},"institutions":[{"id":"https://openalex.org/I4210165634","display_name":"Africa Nazarene University","ror":"https://ror.org/05twfp995","country_code":"KE","type":"education","lineage":["https://openalex.org/I4210165634"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Ombui, Edward","raw_affiliation_strings":["Africa Nazarene University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Africa Nazarene University","institution_ids":["https://openalex.org/I4210165634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014319170","display_name":"Lawrence Muchemi","orcid":"https://orcid.org/0000-0001-5911-5679","observed_orcids":["https://orcid.org/0000-0001-5911-5679"]},"institutions":[{"id":"https://openalex.org/I12859529","display_name":"University of Nairobi","ror":"https://ror.org/02y9nww90","country_code":"KE","type":"education","lineage":["https://openalex.org/I12859529"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Muchemi, Lawrence","raw_affiliation_strings":["University of Nairobi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nairobi","institution_ids":["https://openalex.org/I12859529"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.42309999465942383,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.42309999465942383,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3292999863624573,"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":0.05299999937415123,"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/kenyan-languages","display_name":"Kenyan languages","score":0.9100000262260437},{"id":"https://openalex.org/keywords/luhya","display_name":"Luhya","score":0.5979999899864197},{"id":"https://openalex.org/keywords/dholuo","display_name":"Dholuo","score":0.949999988079071},{"id":"https://openalex.org/keywords/swahili-language","display_name":"Swahili language","score":0.9789999723434448},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.6299999952316284},{"id":"https://openalex.org/keywords/corpus","display_name":"text corpora","score":0.6190000176429749},{"id":"https://openalex.org/keywords/indigenous-stories","display_name":"Indigenous stories","score":0.5590000152587891},{"id":"https://openalex.org/keywords/everyday-language-use","display_name":"everyday language use","score":0.7260000109672546},{"id":"https://openalex.org/keywords/language-documentation","display_name":"language documentation","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C187651312","wikidata":"https://www.wikidata.org/wiki/Q114","display_name":"Kenya","level":2,"score":0.8897206783294678},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5278841257095337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5164632797241211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44683837890625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446652889251709},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19631925225257874},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08826351165771484},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.07280981540679932}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7910/dvn/6n5v1k","doi":"https://doi.org/10.7910/dvn/6n5v1k","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/6n5v1k","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.7910/dvn/6n5v1k","doi":"https://doi.org/10.7910/dvn/6n5v1k","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/6n5v1k","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4381488486","https://openalex.org/W7125393895","https://openalex.org/W4406733688","https://openalex.org/W2223666346","https://openalex.org/W2736098086","https://openalex.org/W7033740617","https://openalex.org/W7098929114","https://openalex.org/W4398906946","https://openalex.org/W2051783146","https://openalex.org/W7166558230"],"abstract_inverted_index":{"This":[0,70],"project":[1],"collected":[2,47,132],"text":[3],"and":[4,22,42,58,68,118,138,171],"speech":[5,142],"corpora":[6],"for":[7,108,112,116,121,149,156,163,169,177],"Languages":[8],"in":[9,93],"Kenya.":[10],"In":[11,30],"KenCorpus":[12],"project,":[13,32],"three":[14],"languages":[15],"were":[16,35,104,131],"strategically":[17],"selected":[18],"i.e.":[19],"Kiswahili,":[20],"Luhya,":[21],"Dholuo.":[23],"The":[24],"Luhya":[25],"Language":[26],"has":[27],"several":[28],"dialects.":[29],"the":[31,49,73,85,94],"3":[33],"dialects":[34],"chosen":[36],"as":[37],"a":[38],"start:":[39],"Lumarachi,":[40],"Logooli":[41],"Lubukusi.":[43],"Primary":[44],"data":[45,97,181],"was":[46],"from":[48,61],"respective":[50],"language":[51,65,91],"communities,":[52],"which":[53,133],"also":[54],"included":[55],"indiginous":[56],"stories":[57],"other":[59,79],"narratives":[60],"student":[62],"compositions,":[63],"native":[64],"media":[66],"stations,":[67],"publishers.":[69],"went":[71],"beyond":[72],"conventional":[74],"religious":[75],"texts":[76,82,103,107,111,115,120],"to":[77,135],"include":[78],"genres":[80],"of":[81,89,101,128,140,180],"that":[83],"made":[84],"corpus":[86],"more":[87],"representative":[88],"everyday":[90],"use":[92],"communities.":[95],"Text":[96],":":[98],"A":[99,126],"total":[100,127,134],"4442":[102],"collected:":[105],"546":[106],"Dholuo,":[109,157],"483":[110],"Luhya-Lumarachi,":[113,164],"135":[114],"Luhya-Lubukusu":[117,170],"359":[119],"Luhya-Logooli.":[122,178],"Spontaneous":[123],"Speech":[124],"data:":[125,143],"1,152":[129],"files":[130,145,152,159,166,173],"176hr":[136],"29min":[137],"46sec":[139],"spontaneous":[141],"104":[144],"(19hr":[146],"10min":[147],"57sec)":[148],"Swahili,":[150],"512":[151],"(99hr":[153],"3min":[154],"8sec)":[155],"138":[158],"(15hr":[160],"37min":[161],"46sec)":[162],"354":[165],"(30hr":[167],"11min)":[168],"44":[172],"(12hr":[174],"26min":[175],"55sec)":[176],"Acknowledgement":[179],"collectors:":[182],"Kiswahili":[183],"-":[184,193,207,215,223],"Rose":[185],"Felynix,":[186],"Khalid":[187],"Kitito,":[188],"Dr.":[189,197,210],"Benard":[190],"Okal":[191],"Luo":[192],"Jotham":[194],"Ondu":[195],"Ajiki,":[196],"Jackline":[198],"Okello,":[199],"Jonathan":[200],"Muga,":[201],"Mercy":[202],"Lavinca":[203],"Oduoll":[204],"Luhyia":[205,213,221],"(Logooli)":[206],"Salano":[208],"Odari,":[209],"Phillip":[211],"Lumwamu":[212],"(Bukusu)":[214],"Mactilda":[216],"Nekesa":[217],"Makana,":[218],"Mulwale":[219],"Martin":[220],"(Marachi)":[222],"Yonah":[224],"Weunda":[225]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-05-24T00:00:00"}
