{"id":"W3099161326","doi":"10.18653/v1/2020.alw-1.17","title":"Towards a Comprehensive Taxonomy and Large-Scale Annotated Corpus for Online Slur Usage","year":2020,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Taxonomy (biology); Pejorative; Natural language processing; Annotation; Artificial intelligence; Information retrieval; Linguistics","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":[0.005899176,0.001345887,0.0008930758,0.01458012,0.003022403,0.002761605,0.001985988,0.002263458,0.006969117],"category_scores_gemma":[0.03379811,0.0008184634,0.0006782903,0.008718437,0.001902641,0.005139336,0.005369043,0.002987267,0.01002039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002198569,"about_ca_system_score_gemma":0.004512649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01051512,"about_ca_topic_score_gemma":0.02313515,"domain_scores_codex":[0.990902,0.003112398,0.001572052,0.001709419,0.002331037,0.0003730904],"domain_scores_gemma":[0.9446985,0.02377545,0.005061368,0.006810743,0.01798637,0.001667653],"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":[0.0006362071,0.001018132,0.06067606,0.01041567,0.0000980457,0.002731966,0.0426933,0.004461918,0.0569828,0.01340096,0.4300393,0.3768455],"study_design_scores_gemma":[0.0001461753,0.0003968947,0.163024,0.00394408,0.0001189956,0.003710544,0.03298289,0.03277075,0.02156168,0.009810912,0.7310114,0.0005217035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3325473,0.005065948,0.250588,0.006554284,0.002055029,0.005813029,0.3351397,0.02108639,0.04115029],"genre_scores_gemma":[0.19312,0.001980305,0.329411,0.001310105,0.0005100946,0.01018816,0.4476515,0.003132227,0.01269662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01458012,"threshold_uncertainty_score":0.0311982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04135385596207682,"score_gpt":0.2491796322261265,"score_spread":0.2078257762640497,"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."}}