{"id":"W7125393895","doi":"10.55492/v6i02.6747","title":"Building Corpora for Low-Resource Kenyan Languages","year":2025,"lang":"","type":"article","venue":"Journal of the Digital Humanities Association of Southern Africa","topic":"ICT in Developing Communities","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Wirtschaftliche Zusammenarbeit und Entwicklung; International Development Research Centre; Rockefeller Foundation","keywords":"Languages of Africa; Kenya; Reading (process); Natural language; Corpus linguistics; Text corpus; Computational linguistics; Language identification","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":[0.003625405,0.0009596851,0.0005317113,0.005786476,0.004455931,0.002065776,0.001567928,0.00105868,0.0196273],"category_scores_gemma":[0.0127365,0.0008460557,0.0004940002,0.004813637,0.001656361,0.003694072,0.004008006,0.001700345,0.006628809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555594,"about_ca_system_score_gemma":0.004532571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01001628,"about_ca_topic_score_gemma":0.0340993,"domain_scores_codex":[0.9971448,0.0009536391,0.0004426252,0.0008103098,0.0004551141,0.0001934618],"domain_scores_gemma":[0.9894803,0.004837859,0.0007798168,0.001650369,0.002877503,0.0003741502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008519169,0.00102186,0.0342701,0.007604052,0.0001581585,0.008594005,0.06909232,0.006941353,0.1379935,0.03553781,0.1788626,0.5190724],"study_design_scores_gemma":[0.0002379856,0.0002579626,0.06789405,0.001496313,0.0001311762,0.002364729,0.02937281,0.00756592,0.03349601,0.00666182,0.8502635,0.0002577617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5200146,0.003961746,0.1315182,0.003608245,0.001501572,0.01549221,0.2113311,0.004155168,0.1084171],"genre_scores_gemma":[0.3287014,0.001974442,0.3438828,0.0007463876,0.0002687205,0.01925889,0.2838762,0.001752363,0.01953873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0196273,"threshold_uncertainty_score":0.06565988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01795061024483665,"score_gpt":0.2419945099350392,"score_spread":0.2240438996902026,"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."}}