{"id":"W4386566992","doi":"10.18653/v1/2023.c3nlp-1.8","title":"Toward Cultural Bias Evaluation Datasets: The Case of Bengali Gender, Religious, and National Identity","year":2023,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bengali; Unavailability; Nationality; Artifact (error); Identity (music); Process (computing); Cultural identity; Computer science; Natural language processing; Artificial intelligence; Psychology; Social psychology; Political science; Statistics; Mathematics; Immigration; Aesthetics","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":[0.01188755,0.0008156142,0.0005694487,0.003716119,0.003426753,0.002954037,0.002584348,0.00192907,0.002158436],"category_scores_gemma":[0.02828376,0.0001958246,0.0007068904,0.003844419,0.001691748,0.002341501,0.00362439,0.001633111,0.00188038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004101466,"about_ca_system_score_gemma":0.003223727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04665584,"about_ca_topic_score_gemma":0.07161816,"domain_scores_codex":[0.9876237,0.006975943,0.001240767,0.001259153,0.002188454,0.0007120338],"domain_scores_gemma":[0.9742182,0.006148982,0.001869561,0.00733204,0.009244106,0.001187138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002468729,0.003083737,0.2298328,0.003430264,0.0006342754,0.002440724,0.01884524,0.01128769,0.0235789,0.03311644,0.3695798,0.3017014],"study_design_scores_gemma":[0.0003548826,0.0006308031,0.2772222,0.0009881456,0.0003218412,0.001628731,0.03084061,0.04300003,0.04512108,0.01487403,0.5847207,0.0002969034],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7342205,0.002447661,0.04454431,0.01101544,0.001532782,0.00388148,0.1403769,0.005940754,0.05604026],"genre_scores_gemma":[0.7196082,0.0004998005,0.07663596,0.001562558,0.0002069983,0.002386141,0.1883973,0.0005059253,0.01019704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04665584,"threshold_uncertainty_score":0.09276855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1445624502315244,"score_gpt":0.3546193864170398,"score_spread":0.2100569361855153,"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."}}