{"id":"W4386566370","doi":"10.18653/v1/2023.vardial-1.15","title":"Dialect and Variant Identification as a Multi-Label Classification Task: A Proposal Based on Near-Duplicate Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Classifier (UML); Identifier; Artificial intelligence; Annotation; Multi-label classification; Identification (biology); Test data; Natural language processing; Pattern recognition (psychology); Machine learning","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":[0.009645657,0.001607875,0.002379494,0.006984501,0.002665836,0.006830855,0.004444504,0.00355791,0.001944519],"category_scores_gemma":[0.02083046,0.0006514268,0.002554684,0.004467602,0.002584868,0.007479997,0.005609614,0.004552337,0.002547887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001797035,"about_ca_system_score_gemma":0.002896118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006534413,"about_ca_topic_score_gemma":0.007400033,"domain_scores_codex":[0.9888203,0.003150869,0.0006203456,0.004104741,0.002630177,0.0006735502],"domain_scores_gemma":[0.9849021,0.004688946,0.001158272,0.004546843,0.004056623,0.0006473109],"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":[0.001142824,0.0008195995,0.04722872,0.0006498497,0.0005664739,0.0009519161,0.003952414,0.01971848,0.03670188,0.02557589,0.01790685,0.8447851],"study_design_scores_gemma":[0.0001494258,0.0007476959,0.02485193,0.0002586152,0.0006206324,0.003223971,0.004034161,0.7400899,0.05008191,0.1228379,0.05268791,0.0004159463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09397895,0.001303267,0.8934806,0.00162835,0.0003837975,0.0004297998,0.0008108985,0.004070183,0.003914188],"genre_scores_gemma":[0.3999346,0.0005001695,0.5852314,0.0009872539,0.000483593,0.0005593257,0.00358899,0.0009248716,0.007789786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009645657,"threshold_uncertainty_score":0.05101174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02967573975349974,"score_gpt":0.3153611143868859,"score_spread":0.2856853746333862,"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."}}