{"id":"W7125517337","doi":"10.55492/v6i02.6736","title":"Mafoko: Structuring and Building Open Multilingual Terminologies for South African NLP","year":2025,"lang":"","type":"article","venue":"Journal of the Digital Humanities Association of Southern Africa","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Pretoria; International Development Research Centre; Nvidia","keywords":"Terminology; Interoperability; Bridging (networking); Consistency (knowledge bases); Structuring; Scalability; Machine translation","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001035674,0.0002927904,0.0006390655,0.0003250861,0.0005266592,0.002582761,0.002945888,0.0001929737,0.000004850368],"category_scores_gemma":[0.002341548,0.0002153829,0.0003292862,0.0002772949,0.0002206997,0.001149861,0.0019269,0.0004631044,4.59925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004762303,"about_ca_system_score_gemma":0.0003355813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000147502,"about_ca_topic_score_gemma":0.000005647345,"domain_scores_codex":[0.9975317,0.0001142066,0.001094636,0.0002868887,0.0005710063,0.000401624],"domain_scores_gemma":[0.9945014,0.0007292108,0.003539287,0.0003386042,0.0008467707,0.00004470274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001156502,0.0007041099,0.02119423,0.002173696,0.003244006,0.00002899178,0.3633866,0.0002265348,0.00441771,0.09135634,0.003071332,0.5090399],"study_design_scores_gemma":[0.00613566,0.00149302,0.002680943,0.006265721,0.001059153,0.00007297107,0.1231175,0.004247935,0.04416298,0.7908347,0.0181339,0.001795575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9083239,0.01598758,0.05152139,0.004178774,0.003881731,0.002918982,0.002257027,0.0002634824,0.01066709],"genre_scores_gemma":[0.9752957,0.00001360368,0.01864836,0.00006753812,0.0001396785,0.000005602025,7.155198e-7,0.00002095821,0.005807895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6994783,"threshold_uncertainty_score":0.9984527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02697340096356203,"score_gpt":0.2787776361997294,"score_spread":0.2518042352361674,"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."}}