{"id":"W3136687158","doi":"10.1162/tacl","title":"MasakhaNER: Named entity recognition for African languages","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Topic Modeling","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Named-entity recognition; Computer science; Natural language processing; Linguistics; Entity linking; Artificial intelligence; Philosophy; Engineering; Task (project management)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001420851,0.001360738,0.001130276,0.002069668,0.001018087,0.002111075,0.001503414,0.001045638,0.02353509],"category_scores_gemma":[0.003542874,0.0007511034,0.001302224,0.002103394,0.0003070995,0.004889613,0.002689093,0.001414575,0.01943886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005751435,"about_ca_system_score_gemma":0.001036831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004078217,"about_ca_topic_score_gemma":0.004219768,"domain_scores_codex":[0.9991685,0.0001741562,0.00009340651,0.0002852327,0.0001704686,0.0001082337],"domain_scores_gemma":[0.9990131,0.000367034,0.00008103464,0.0002640874,0.000169254,0.0001055995],"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":[0.002119582,0.0002970383,0.006248169,0.001492957,0.0003815564,0.0008769887,0.0007347293,0.004639139,0.03559159,0.01240619,0.4418837,0.4933284],"study_design_scores_gemma":[0.000577743,0.0005520554,0.01368734,0.0003211018,0.0004777099,0.001589485,0.001131978,0.2417818,0.1295267,0.02896586,0.5810915,0.0002967881],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.04540338,0.002435979,0.3964216,0.001798718,0.0008503368,0.0007869754,0.1269436,0.4138005,0.01155897],"genre_scores_gemma":[0.2055086,0.001424475,0.4690976,0.0006962378,0.0002294158,0.001192612,0.2837031,0.01255638,0.02559173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02353509,"threshold_uncertainty_score":0.07873267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0201344719929059,"score_gpt":0.2364009823153819,"score_spread":0.216266510322476,"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."}}