{"id":"W4381488486","doi":"10.21248/jlcl.36.2023.243","title":"Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks","year":2023,"lang":"en","type":"article","venue":"LDV-Forum/Journal for language technology and computational linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; Rockefeller Foundation","keywords":"Swahili; Computer science; Natural language processing; Artificial intelligence; Machine translation; Question answering; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007234946,0.0009770859,0.0007365338,0.003590302,0.002843409,0.001187876,0.001027072,0.001260876,0.01660573],"category_scores_gemma":[0.003081252,0.0005280144,0.0004245634,0.00418424,0.0009350018,0.001748242,0.00196271,0.001046539,0.007846489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314613,"about_ca_system_score_gemma":0.00336588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03668765,"about_ca_topic_score_gemma":0.1071375,"domain_scores_codex":[0.9991762,0.0001955206,0.0001147234,0.0002396256,0.0001589872,0.0001148591],"domain_scores_gemma":[0.9986116,0.0005480606,0.0001320191,0.0001648682,0.0004034864,0.0001399907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00146657,0.0006637657,0.02510936,0.01170538,0.0002382846,0.006630379,0.01901898,0.001563213,0.04224938,0.007749701,0.7238275,0.1597776],"study_design_scores_gemma":[0.0002358912,0.0001002283,0.08415934,0.0008212138,0.00009326988,0.001643553,0.007765471,0.001756058,0.009320053,0.001089877,0.8928866,0.0001284564],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1440764,0.002267248,0.004205041,0.0008487132,0.0003658592,0.00131848,0.8203171,0.001578988,0.02502207],"genre_scores_gemma":[0.08477946,0.0006837235,0.01497773,0.0002874286,0.00005461799,0.002744656,0.8888048,0.0003857023,0.007281913],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03668765,"threshold_uncertainty_score":0.07294822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008866185083867504,"score_gpt":0.2992442199912029,"score_spread":0.2903780349073354,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}