{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009785201,0.001269626,0.0007671447,0.002034012,0.0005829095,0.001804461,0.0006501398,0.0006190207,0.004528821],"category_scores_gemma":[0.005788822,0.0003007717,0.000751354,0.001568515,0.001011698,0.00188724,0.002525319,0.001371994,0.002001193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003493159,"about_ca_system_score_gemma":0.000542142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002507324,"about_ca_topic_score_gemma":0.003007711,"domain_scores_codex":[0.9990551,0.0003163248,0.00005040768,0.0002476657,0.0001815264,0.0001489951],"domain_scores_gemma":[0.9973238,0.001272262,0.0002680636,0.0003435639,0.0006110751,0.0001812061],"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":[0.001969853,0.000420169,0.02487464,0.0004349149,0.0002332912,0.0004839282,0.001961654,0.0197824,0.04323407,0.009982073,0.01792269,0.8787003],"study_design_scores_gemma":[0.00007395408,0.00058294,0.05672537,0.0001981261,0.0001779794,0.0007637425,0.003533742,0.8554797,0.01836847,0.05174169,0.01213917,0.0002151209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.326176,0.001545797,0.6616581,0.0007853828,0.0003118242,0.0001274377,0.002259594,0.001687321,0.005448524],"genre_scores_gemma":[0.8721196,0.0007975402,0.116606,0.0001224513,0.000189212,0.0001791107,0.004383915,0.0003130697,0.005289084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004528821,"threshold_uncertainty_score":0.01515043,"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."}}