{"id":"W4385572824","doi":"10.18653/v1/2022.emnlp-main.298","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Blessing; Art history; Art; Philosophy; Theology","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":[0.003223742,0.002263191,0.001213798,0.002840139,0.001050878,0.002360564,0.003510506,0.001789291,0.02167353],"category_scores_gemma":[0.005221547,0.000867814,0.001939701,0.002263866,0.0004832257,0.004563005,0.005373893,0.003114714,0.01915806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008748185,"about_ca_system_score_gemma":0.00195623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007894733,"about_ca_topic_score_gemma":0.008419086,"domain_scores_codex":[0.9987363,0.0004099604,0.00008616042,0.0003851317,0.0002424987,0.0001399086],"domain_scores_gemma":[0.9989963,0.0003232028,0.00006167951,0.0003465404,0.000166338,0.0001058886],"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":[0.001402069,0.000485465,0.002151825,0.0006207321,0.0005381552,0.0006136525,0.0003344141,0.02858535,0.00794386,0.01159349,0.2638772,0.6818538],"study_design_scores_gemma":[0.0004291649,0.0004165957,0.002047257,0.0001798827,0.0002126347,0.0005269257,0.0003179451,0.7569197,0.02484318,0.0425544,0.171388,0.0001643819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01635776,0.002956065,0.647863,0.001228606,0.0008305451,0.0006270527,0.01548906,0.3034765,0.01117152],"genre_scores_gemma":[0.159641,0.002676352,0.6746109,0.001143744,0.0003176971,0.002062161,0.1114332,0.01235686,0.03575818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02167353,"threshold_uncertainty_score":0.07250518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04522403817423372,"score_gpt":0.2313573381089553,"score_spread":0.1861332999347216,"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."}}