{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002158533,0.0001265894,0.0001566779,0.00007986696,0.0002469116,0.000339389,0.0007837263,0.00007511444,0.00007268566],"category_scores_gemma":[0.001432684,0.0001410584,0.000111455,0.0003835731,0.00004997353,0.0002983306,0.000374605,0.0001313668,0.00003562919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004560845,"about_ca_system_score_gemma":0.000144541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002080224,"about_ca_topic_score_gemma":0.0007877084,"domain_scores_codex":[0.997349,0.001359941,0.0002575196,0.0005214994,0.0002433687,0.000268641],"domain_scores_gemma":[0.996229,0.0008529641,0.0001440042,0.001255991,0.001406657,0.0001113623],"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":[0.000005518246,0.0004185493,0.0008608498,0.000090507,0.000045578,0.00001569532,0.008609824,0.0000198591,0.0134828,0.2890409,0.001196654,0.6862133],"study_design_scores_gemma":[0.001856944,0.000001255804,0.002623682,0.0007627472,0.00005031754,0.00007221042,0.0008678944,0.3031142,0.5677477,0.04599836,0.07596359,0.0009411897],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03155953,0.0003808972,0.9299725,0.01101357,0.0001536726,0.0001827085,0.00001845778,0.0002399808,0.02647865],"genre_scores_gemma":[0.621884,0.00007520109,0.3714253,0.0002033539,0.00002568773,0.00005163038,0.0001205594,0.00001416625,0.006200082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.685272,"threshold_uncertainty_score":0.5752193,"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."}}