{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004316772,0.002208157,0.001396557,0.004716551,0.002167372,0.002711142,0.002802291,0.001976445,0.01204532],"category_scores_gemma":[0.01106898,0.0007505238,0.001626501,0.003952262,0.0008489212,0.007309927,0.005194385,0.003049025,0.01528019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111183,"about_ca_system_score_gemma":0.002569595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01183061,"about_ca_topic_score_gemma":0.01377255,"domain_scores_codex":[0.9968129,0.001133605,0.0003197939,0.0008801511,0.0005432417,0.0003103293],"domain_scores_gemma":[0.9954313,0.001547778,0.0003677019,0.001680911,0.0006103562,0.0003618619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001796957,0.0008152204,0.01334305,0.002174138,0.0004458876,0.000940068,0.0009502239,0.01420509,0.01275374,0.01050303,0.7293999,0.2126728],"study_design_scores_gemma":[0.0009669065,0.0006499147,0.03058103,0.000705547,0.0004005299,0.002177175,0.001907332,0.26418,0.05402829,0.02406138,0.6198926,0.0004492187],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1273443,0.005116911,0.1005722,0.005284137,0.001912115,0.00180481,0.5555237,0.1842263,0.01821544],"genre_scores_gemma":[0.1003961,0.0009504109,0.1063696,0.0005847203,0.0002207571,0.001337104,0.7819177,0.001841533,0.00638212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01204532,"threshold_uncertainty_score":0.0402956,"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."}}