{"id":"https://openalex.org/W7217658488","doi":null,"title":"Development of the Annotated Swahili Digraph Corpus Using a CNN-Based Digraph Extraction Model","display_name":"Development of the Annotated Swahili Digraph Corpus Using a CNN-Based Digraph Extraction Model","publication_year":2024,"publication_date":"2024-12-31","ids":{"openalex":"https://openalex.org/W7217658488"},"language":"en","primary_location":{"id":"pmh:oai:ijsrcse.isroset.org:article/604","doi":null,"is_oa":true,"landing_page_url":"https://ijsrcse.isroset.org/index.php/j/article/view/604","pdf_url":"https://ijsrcse.isroset.org/index.php/j/article/download/604/604","source":{"id":"https://openalex.org/S4210199740","display_name":"International Journal of Scientific Research in Computer Sciences and Engineering","issn_l":"2320-7639","issn":["2320-7639"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2320-7639","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ijsrcse.isroset.org/index.php/j/article/download/604/604","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086696761","display_name":"Tirus Muya Maina","orcid":"https://orcid.org/0000-0001-7378-9215","observed_orcids":["https://orcid.org/0000-0001-7378-9215","https://orcid.org/0000-0001-8265-2958"]},"institutions":[{"id":"https://openalex.org/I3133159679","display_name":"Murang'a University of Technology","ror":"https://ror.org/057k4ej49","country_code":"KE","type":"education","lineage":["https://openalex.org/I3133159679"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Maina, Tirus Muya","raw_affiliation_strings":["Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya","institution_ids":["https://openalex.org/I3133159679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040248606","display_name":"Aaron Mogeni Oirere","orcid":"https://orcid.org/0000-0002-3167-9429","observed_orcids":["https://orcid.org/0000-0002-3167-9429"]},"institutions":[{"id":"https://openalex.org/I3133159679","display_name":"Murang'a University of Technology","ror":"https://ror.org/057k4ej49","country_code":"KE","type":"education","lineage":["https://openalex.org/I3133159679"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Oirere, Aaron Mogeni","raw_affiliation_strings":["Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya","institution_ids":["https://openalex.org/I3133159679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035633519","display_name":"Stephen Kahara","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3133159679","display_name":"Murang'a University of Technology","ror":"https://ror.org/057k4ej49","country_code":"KE","type":"education","lineage":["https://openalex.org/I3133159679"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Kahara, Stephen","raw_affiliation_strings":["Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Murang\u2019a University of Technology, Murang\u2019a, Kenya","institution_ids":["https://openalex.org/I3133159679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3133159679"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9169999957084656,"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":0.9169999957084656,"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":0.06629999727010727,"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":0.00419999985024333,"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/swahili-language","display_name":"Swahili language","score":0.9549999833106995},{"id":"https://openalex.org/keywords/directed-graphs","display_name":"directed graphs","score":0.9570000171661377},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.781000018119812},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8539999723434448},{"id":"https://openalex.org/keywords/swahili-phonology","display_name":"Swahili phonology","score":0.5789999961853027},{"id":"https://openalex.org/keywords/vowel-distribution","display_name":"vowel distribution","score":0.5730000138282776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8619999885559082},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.5960000157356262},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.8569999933242798}],"concepts":[{"id":"https://openalex.org/C2779913364","wikidata":"https://www.wikidata.org/wiki/Q7838","display_name":"Swahili","level":2,"score":0.9093000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307000160217285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.642799973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752999782562256},{"id":"https://openalex.org/C2779145032","wikidata":"https://www.wikidata.org/wiki/Q191494","display_name":"Digraph","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ijsrcse.isroset.org:article/604","doi":null,"is_oa":true,"landing_page_url":"https://ijsrcse.isroset.org/index.php/j/article/view/604","pdf_url":"https://ijsrcse.isroset.org/index.php/j/article/download/604/604","source":{"id":"https://openalex.org/S4210199740","display_name":"International Journal of Scientific Research in Computer Sciences and Engineering","issn_l":"2320-7639","issn":["2320-7639"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2320-7639","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ijsrcse.isroset.org:article/604","doi":null,"is_oa":true,"landing_page_url":"https://ijsrcse.isroset.org/index.php/j/article/view/604","pdf_url":"https://ijsrcse.isroset.org/index.php/j/article/download/604/604","source":{"id":"https://openalex.org/S4210199740","display_name":"International Journal of Scientific Research in Computer Sciences and Engineering","issn_l":"2320-7639","issn":["2320-7639"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2320-7639","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7217658488.pdf","grobid_xml":"https://content.openalex.org/works/W7217658488.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6906731272","https://openalex.org/W7217202965","https://openalex.org/W7216746767","https://openalex.org/W4416017204","https://openalex.org/W4407364809","https://openalex.org/W2182193419","https://openalex.org/W2114499288","https://openalex.org/W2401271873","https://openalex.org/W4409403733","https://openalex.org/W4377140520"],"abstract_inverted_index":{"This":[0,24,182],"study":[1],"undertakes":[2],"the":[3,6,20,31,38,61,71,75,120,123,150,173,221,226,236],"development":[4],"of":[5,22,33,65,70,80,122,135,190],"Annotated":[7],"Swahili":[8,39,124,128,153,227],"Digraph":[9,129],"Corpus,":[10],"utilizing":[11],"a":[12,27,87,132,187],"convolutional":[13],"neural":[14],"network-based":[15],"model":[16,55],"specifically":[17,118],"designed":[18],"for":[19,37,45,108,169,202,224],"extraction":[21,62],"digraphs.":[23,145],"initiative":[25],"addresses":[26],"significant":[28],"gap":[29],"in":[30,48,86,98,235],"availability":[32],"dedicated":[34,215],"digraph":[35],"corpora":[36],"language,":[40,88,228],"which":[41],"is":[42],"increasingly":[43],"needed":[44],"various":[46],"applications":[47],"Natural":[49],"Language":[50],"Processing":[51],"(NLP).":[52],"The":[53,126],"CNN-based":[54],"was":[56],"accurately":[57],"crafted":[58],"to":[59,119,141,197,219,231],"optimize":[60],"and":[63,89,96,104,112,163,180,195,210],"classification":[64],"digraphs,":[66],"taking":[67],"full":[68],"advantage":[69],"annotated":[72,140,184],"features":[73,149],"within":[74],"corpus.":[76],"Digraphs":[77],"are":[78,106],"pairs":[79],"letters":[81],"that":[82,116],"create":[83],"distinct":[84],"sounds":[85],"Swahili`s":[90],"linguistic":[91,200],"structure":[92],"presents":[93],"unique":[94],"challenges":[95],"requirements":[97],"this":[99,147,214],"regard.":[100],"Therefore,":[101],"specialized":[102],"tools":[103],"models":[105],"essential":[107],"ensuring":[109],"accurate":[110,199],"transcription":[111],"efficient":[113],"speech":[114,211],"recognition":[115],"cater":[117],"nuances":[121],"language.":[125],"resulting":[127],"Corpus":[130],"comprises":[131],"comprehensive":[133],"collection":[134],"31,197":[136],"words,":[137],"each":[138],"systematically":[139],"highlight":[142],"their":[143],"respective":[144],"Notably,":[146],"corpus":[148,185],"nine":[151],"key":[152],"digraphs:":[154],"\"ch,\"":[155],"\"dh,\"":[156],"\"gh,\"":[157],"\"kh,\"":[158],"\"ng\u2019,\"":[159],"\"ny,\"":[160],"\"sh,\"":[161],"\"th,\"":[162],"\"ng.\"":[164],"Furthermore,":[165],"it":[166],"includes":[167],"annotations":[168],"vowel":[170],"distribution,":[171],"showcasing":[172],"core":[174],"vowels":[175],"\"a,\"":[176],"\"e,\"":[177],"\"i,\"":[178],"\"o,\"":[179],"\"u.\"":[181],"detailed":[183],"supports":[186],"wide":[188],"array":[189],"NLP":[191],"applications,":[192],"enabling":[193],"researchers":[194],"developers":[196],"utilize":[198],"data":[201],"tasks":[203],"such":[204],"as":[205],"text":[206],"processing,":[207],"machine":[208],"translation,":[209],"synthesis.":[212],"Through":[213],"effort,":[216],"we":[217],"aim":[218],"enhance":[220],"resources":[222],"available":[223],"processing":[225],"ultimately":[229],"contributing":[230],"its":[232],"greater":[233],"accessibility":[234],"digital":[237],"landscape.":[238]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2026-10-03T00:00:00"}