{"id":"W2948877201","doi":"10.18653/v1/s19-2136","title":"UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of British Columbia","funders":"","keywords":"SemEval; Offensive; Task (project management); Macro; Computer science; Artificial intelligence; Natural language processing; Ensemble learning; Machine learning; Training set; Host (biology); Mathematics; Operations research; Biology","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":[0.006813974,0.00241392,0.001883622,0.00218773,0.001500965,0.001824064,0.00153919,0.00263629,0.01536012],"category_scores_gemma":[0.01304447,0.0005005389,0.0009730045,0.001800529,0.0005474373,0.00283245,0.003415863,0.002593576,0.02032445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008375659,"about_ca_system_score_gemma":0.0008732242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005791001,"about_ca_topic_score_gemma":0.01062955,"domain_scores_codex":[0.9957495,0.001643268,0.0001807369,0.001073161,0.0008666203,0.0004866757],"domain_scores_gemma":[0.9926841,0.002323896,0.0002454998,0.002517629,0.001617623,0.0006112352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002615908,0.002643688,0.02032619,0.0007794691,0.0005254522,0.0007790269,0.000526915,0.02580627,0.02081078,0.001062866,0.4367973,0.4873263],"study_design_scores_gemma":[0.001029729,0.002525446,0.05612808,0.0002697079,0.0003096104,0.00122357,0.001651934,0.6661557,0.07646762,0.007366944,0.1866161,0.0002556625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6741408,0.004028979,0.09883227,0.005040031,0.005489338,0.001874085,0.08249374,0.06155706,0.06654366],"genre_scores_gemma":[0.6382324,0.0005667365,0.1184711,0.001244124,0.0008876706,0.001099438,0.1926354,0.003624403,0.0432387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01536012,"threshold_uncertainty_score":0.05138469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07137152691733431,"score_gpt":0.2596168888994028,"score_spread":0.1882453619820685,"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."}}