{"id":"W4385734113","doi":"10.18653/v1/2023.wassa-1.25","title":"Identifying Slurs and Lexical Hate Speech via Light-Weight Dimension Projection in Embedding Space","year":2023,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Utterance; Dimension (graph theory); Computer science; Representation (politics); Embedding; Space (punctuation); Identity (music); Natural language processing; Word (group theory); Identification (biology); Speech recognition; Artificial intelligence; Linguistics; Mathematics; Aesthetics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004981178,0.0001376848,0.0001402725,0.0004338331,0.0001841154,0.0002372007,0.000175182,0.00009796287,0.00001067444],"category_scores_gemma":[0.00002966768,0.0001229721,0.00003749887,0.001243278,0.00001761797,0.0006950663,0.0002321152,0.000189082,0.0002252078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005974274,"about_ca_system_score_gemma":0.00001800595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002137858,"about_ca_topic_score_gemma":0.0001156316,"domain_scores_codex":[0.9986027,0.00006787648,0.0002036815,0.0004911869,0.0002744047,0.0003601694],"domain_scores_gemma":[0.9995447,0.00004001152,0.00004931607,0.0002442998,0.00003339569,0.00008830172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007589251,0.0001723325,0.008581823,0.0001805468,0.0000484347,0.0006318757,0.006466344,0.0004977738,0.5892441,0.01928907,0.00471943,0.3700924],"study_design_scores_gemma":[0.0007817982,0.0001847346,0.01434054,0.0001752158,0.000008979815,0.0002558607,0.0003211688,0.6437293,0.327727,0.00910675,0.002827497,0.0005412116],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7833165,0.00004488807,0.2110492,0.001724538,0.0009979529,0.0002933163,1.589965e-7,0.000855002,0.001718437],"genre_scores_gemma":[0.9772013,0.00007187156,0.02015442,0.00006392108,0.00009463153,0.00001759277,0.000002363944,0.00001569888,0.002378138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6432315,"threshold_uncertainty_score":0.5014659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01690883462038482,"score_gpt":0.2701923306497711,"score_spread":0.2532834960293863,"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."}}