{"id":"W7133071557","doi":"","title":"Natural Language Processing for Slang","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Swearing, Euphemism, Multilingualism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Slang; Natural language; Semantic interpretation; Computational linguistics; Lexicon; Natural language understanding; Interpretation (philosophy); Semantics (computer science)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007971581,0.0005388401,0.0005365894,0.0002055886,0.000850659,0.0007325339,0.0006377097,0.000686597,0.0003263499],"category_scores_gemma":[0.00105353,0.0005597904,0.0003805135,0.0006748101,0.0001725525,0.0002149724,0.00006774678,0.0008758365,0.0002480613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002982331,"about_ca_system_score_gemma":0.0009822726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004384147,"about_ca_topic_score_gemma":0.004469698,"domain_scores_codex":[0.9967561,0.00008632561,0.0004558495,0.0009824237,0.000812966,0.0009063408],"domain_scores_gemma":[0.9984109,0.0002988191,0.0004440284,0.000301007,0.0003531993,0.0001920285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00007317017,0.00003267053,0.00001352871,0.00164828,0.00007428994,0.0000293825,0.9226902,0.000004351528,0.009678506,0.0003103398,0.001410671,0.06403457],"study_design_scores_gemma":[0.0004724532,0.00004140963,0.0001089114,0.00175173,0.0003935176,0.000003844188,0.9396097,0.009360579,0.009488444,0.000219594,0.03756353,0.000986296],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8886954,0.05284099,0.00006164618,0.0007666246,0.00769821,0.001608871,0.00001525118,0.0005309153,0.0477821],"genre_scores_gemma":[0.7187413,0.00008954953,0.0009965864,0.0001039068,0.002193215,0.0001069334,0.0002741772,0.0001254333,0.2773689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2295868,"threshold_uncertainty_score":0.9996853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02659771207760139,"score_gpt":0.461068815370924,"score_spread":0.4344711032933226,"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."}}