{"id":"W3207937903","doi":"10.1162/tacl_a_00416","title":"MasakhaNER: Named Entity Recognition for African Languages","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Google (Canada)","funders":"","keywords":"Computer science; Named-entity recognition; Variety (cybernetics); Natural language processing; Artificial intelligence; Representation (politics); Code (set theory); Quality (philosophy); Data science; Information retrieval; Programming language; Task (project management); Political science","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":[0.0002995397,0.00007146581,0.0001228598,0.00004780295,0.0002264105,0.00005390561,0.0002470766,0.00006072634,0.000005390952],"category_scores_gemma":[0.001869988,0.0000714427,0.0001838769,0.0002182761,0.00001251399,0.00005027034,0.00001382188,0.00007257163,0.00000198714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195031,"about_ca_system_score_gemma":0.0001753815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001374625,"about_ca_topic_score_gemma":0.0000269326,"domain_scores_codex":[0.9990935,0.00004991873,0.0002752571,0.000180285,0.0002706065,0.0001304221],"domain_scores_gemma":[0.9969689,0.0009105659,0.0002503044,0.0001797331,0.001663971,0.00002657047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000045383,0.0006177434,0.001577006,0.0003284212,0.0005459526,0.000001036574,0.001832302,0.5917858,0.0004261813,0.3616296,0.001735535,0.03947499],"study_design_scores_gemma":[0.0009757116,0.00004475181,0.001273116,0.0000367397,0.0001340564,0.000002449673,0.0001353678,0.7804016,0.003815849,0.200266,0.01271559,0.0001986673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008115541,0.0000276095,0.995745,0.000957865,0.001097294,0.0002453187,0.0002995583,0.0000540844,0.0007617223],"genre_scores_gemma":[0.7305915,0.000002450735,0.2682015,0.00008969352,0.0001586911,0.00003445497,0.00006995219,0.000007012081,0.0008448005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7297799,"threshold_uncertainty_score":0.2913349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0247748537854371,"score_gpt":0.274549278675741,"score_spread":0.2497744248903039,"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."}}