{"id":"W6976775207","doi":"10.60692/rwdwm-ste41","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Named-entity recognition; Task (project management); Transfer of learning; Benchmark (surveying); Transfer (computing); Cover (algebra); Training set; Sequence labeling","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":[0.0006550551,0.0001192994,0.0001492775,0.0002854541,0.0004506602,0.0002396325,0.0003821712,0.00004387788,0.0000377779],"category_scores_gemma":[0.00001803323,0.0001179711,0.00009363952,0.0003519791,0.000006211727,0.001032159,0.0001207758,0.0001501807,0.0001604391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001914047,"about_ca_system_score_gemma":0.00003766147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003666903,"about_ca_topic_score_gemma":4.653648e-8,"domain_scores_codex":[0.9985582,0.0001221174,0.0004607932,0.000195314,0.0003899216,0.0002736918],"domain_scores_gemma":[0.9993952,0.00001398211,0.0001217898,0.0002768166,0.0001286698,0.00006357375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002539937,0.00003169737,0.03036985,0.002031738,0.0002126226,0.00002151244,0.7427114,0.09749603,0.00003270343,0.01167579,0.0006258358,0.1145368],"study_design_scores_gemma":[0.002005883,0.0001256399,0.0008987708,0.00004392945,0.00002728193,0.00008006131,0.009900183,0.9753894,0.0003438045,0.00005002928,0.01071954,0.0004154973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1526153,0.000002997865,0.8446478,0.0000647078,0.0006271889,0.0004495553,0.00002848063,0.0003328214,0.001231126],"genre_scores_gemma":[0.9953701,5.964795e-8,0.003863279,0.00008580903,0.00005334562,0.0003427927,0.00003116023,0.000006713612,0.0002467011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8778933,"threshold_uncertainty_score":0.4810724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388125223713194,"score_gpt":0.2027361766165257,"score_spread":0.1488549243793938,"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."}}