{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005993653,0.0001258101,0.0001698334,0.00003834614,0.0001159002,0.0001167059,0.0002465104,0.00005256649,0.00001902293],"category_scores_gemma":[0.00002396968,0.0001117813,0.00005082104,0.0002619577,0.00002432268,0.0002306711,0.0001604039,0.0000923715,0.00002225765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001195621,"about_ca_system_score_gemma":0.00004160254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003607179,"about_ca_topic_score_gemma":0.0000341003,"domain_scores_codex":[0.9990665,0.00002627551,0.0001598418,0.0003770508,0.0001129875,0.0002572958],"domain_scores_gemma":[0.9994276,0.00003948604,0.00005098816,0.000176572,0.0001186557,0.000186697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002350118,0.0003805116,0.0007242546,0.0002056125,0.0001371351,0.00007757685,0.002792831,0.0001532446,0.03048743,0.01013666,0.02336978,0.9312999],"study_design_scores_gemma":[0.00138183,0.0005199281,0.001334809,0.000009511058,0.000009966543,0.00002400915,0.0001851147,0.3297054,0.009615618,0.0003244302,0.6566304,0.0002590491],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08237073,0.00009169483,0.9127101,0.00306122,0.0001705189,0.0005000304,0.00003905541,0.000319151,0.0007375015],"genre_scores_gemma":[0.3459839,0.00004717094,0.6439833,0.008767149,0.0002599843,0.0001024986,0.00004560224,0.00002251601,0.0007879307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9310409,"threshold_uncertainty_score":0.4558309,"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."}}