{"id":"https://openalex.org/W3153132431","doi":"https://doi.org/10.1109/ictas50802.2021.9395011","title":"isiZulu Word Embeddings","display_name":"isiZulu Word Embeddings","publication_year":2021,"publication_date":"2021-03-01","ids":{"openalex":"https://openalex.org/W3153132431","doi":"https://doi.org/10.1109/ictas50802.2021.9395011","mag":"3153132431"},"language":"en","primary_location":{"id":"doi:10.1109/ictas50802.2021.9395011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas50802.2021.9395011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Conference on Information Communications Technology and Society (ICTAS)","raw_type":"proceedings-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/A5018527836","display_name":"Sibonelo Dlamini","orcid":null},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Sibonelo Dlamini","raw_affiliation_strings":["University of KwaZulu-Natal, Durban, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of KwaZulu-Natal, Durban, South Africa","institution_ids":["https://openalex.org/I95023434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086607089","display_name":"Edgar Jembere","orcid":"https://orcid.org/0000-0003-1776-1925"},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Edgar Jembere","raw_affiliation_strings":["University of KwaZulu-Natal, Durban, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of KwaZulu-Natal, Durban, South Africa","institution_ids":["https://openalex.org/I95023434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084841179","display_name":"Anban Pillay","orcid":"https://orcid.org/0000-0001-7160-6972"},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Anban Pillay","raw_affiliation_strings":["University of KwaZulu-Natal, Durban, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of KwaZulu-Natal, Durban, South Africa","institution_ids":["https://openalex.org/I95023434"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080128974","display_name":"Brett van Niekerk","orcid":"https://orcid.org/0000-0003-1050-4256"},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Brett van Niekerk","raw_affiliation_strings":["University of KwaZulu-Natal, Durban, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of KwaZulu-Natal, Durban, South Africa","institution_ids":["https://openalex.org/I95023434"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95023434"],"apc_list":null,"apc_paid":null,"fwci":0.8394,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78084019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.8329383730888367},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.8183353543281555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7498376965522766},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7257087826728821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7173743844032288},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5518039464950562},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.547053873538971},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4944431781768799},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4785900115966797},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.46863245964050293},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4685210883617401},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4434930980205536},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4387494921684265},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4320867955684662},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3340151309967041},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10113820433616638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8329383730888367},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8183353543281555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7498376965522766},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7257087826728821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7173743844032288},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5518039464950562},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.547053873538971},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4944431781768799},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4785900115966797},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46863245964050293},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4685210883617401},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4434930980205536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4387494921684265},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4320867955684662},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3340151309967041},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10113820433616638},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictas50802.2021.9395011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictas50802.2021.9395011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Conference on Information Communications Technology and Society (ICTAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2067438047","https://openalex.org/W2141599568","https://openalex.org/W2147152072","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2251803266","https://openalex.org/W2270593706","https://openalex.org/W2408387521","https://openalex.org/W2493916176","https://openalex.org/W2512498397","https://openalex.org/W2740654950","https://openalex.org/W2747424680","https://openalex.org/W2787481916","https://openalex.org/W2932675979","https://openalex.org/W2950577311","https://openalex.org/W2956530858","https://openalex.org/W2964085268","https://openalex.org/W2998704965","https://openalex.org/W3105248300","https://openalex.org/W4285719527","https://openalex.org/W4298857951","https://openalex.org/W6636510571","https://openalex.org/W6680532216","https://openalex.org/W6680890276","https://openalex.org/W6713952965","https://openalex.org/W6723250868","https://openalex.org/W6743359967","https://openalex.org/W6748355100"],"related_works":["https://openalex.org/W4388926080","https://openalex.org/W2946409105","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W4388996947","https://openalex.org/W3133567596","https://openalex.org/W2798009317","https://openalex.org/W3203949288","https://openalex.org/W4382201653","https://openalex.org/W3175524270"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,51,113,164],"are":[2],"currently":[3],"the":[4,23,87,101,108,123,151,158,174,179,193,200],"most":[5],"popular":[6,72],"vector":[7],"space":[8],"model":[9,177,195],"in":[10,114,165],"Natural":[11],"Language":[12],"Processing.":[13],"How":[14],"we":[15,69,136],"encode":[16],"words":[17],"is":[18,57,107,144,157],"important":[19],"because":[20],"it":[21,191],"affects":[22],"performance":[24],"of":[25,103,150],"many":[26],"downstream":[27],"tasks":[28],"such":[29],"as":[30,183],"Machine":[31],"Translation":[32],"(MT),":[33],"Information":[34],"Retrieval":[35],"(IR)":[36],"and":[37,78,81,83,119],"Automatic":[38],"Speech":[39],"Recognition":[40],"(ASR).":[41],"While":[42],"much":[43],"focus":[44],"has":[45],"been":[46,117],"placed":[47],"on":[48,86,199],"constructing":[49],"word":[50,73,98,112,163],"for":[52,160],"English,":[53],"very":[54],"little":[55],"attention":[56],"paid":[58],"to":[59,95,122,133,146,154],"under-resourced":[60],"languages,":[61],"especially":[62],"native":[63],"African":[64],"languages.":[65],"In":[66],"this":[67,106,186],"paper":[68],"select":[70],"four":[71,152],"embedding":[74],"models":[75,153],"(Word2Vec":[76],"CBOW":[77],"Skip-Gram;":[79],"FastText":[80],"GloVe)":[82],"train":[84],"them":[85],"10":[88],"million":[89],"token":[90],"isiZulu":[91,97,115,162],"National":[92],"Corpus":[93],"(INC)":[94],"create":[96,126],"embeddings.":[99],"To":[100],"best":[102,159,198],"our":[104],"knowledge,":[105],"first":[109],"time":[110],"that":[111,173],"have":[116],"constructed":[118],"made":[120],"available":[121],"public.":[124],"We":[125,171],"a":[127,166],"semantic":[128,187],"similarity":[129,188],"data":[130,142],"set":[131,143],"analogous":[132],"WordSim353,":[134],"which":[135,156,196],"also":[137],"make":[138],"publicly":[139],"available.":[140],"This":[141],"used":[145],"conduct":[147],"an":[148],"evaluation":[149],"determine":[155],"creating":[161],"low-resource":[167],"(small":[168],"corpus)":[169],"setting.":[170],"found":[172],"Word2Vec":[175],"Skip-Gram":[176],"produced":[178],"highest":[180],"quality":[181],"embeddings,":[182],"measured":[184],"by":[185],"task.":[189,203],"However,":[190],"was":[192],"GloVe":[194],"performed":[197],"nearest":[201],"neighbours":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}