{"id":"W4389483684","doi":"10.1016/j.procs.2023.10.021","title":"FreCDo: A Large Corpus for French Cross-Domain Dialect Identification","year":2023,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Support vector machine; Discriminative model; Classifier (UML); Identification (biology); Natural language processing; Domain (mathematical analysis); Word (group theory); Task (project management); Linguistics","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":[0.001618292,0.001285038,0.0007263771,0.007300265,0.001828663,0.00169601,0.001064358,0.001540584,0.01207978],"category_scores_gemma":[0.006965231,0.0002938395,0.0006507486,0.004009724,0.0007119108,0.001514874,0.001787832,0.0009831191,0.007820887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178465,"about_ca_system_score_gemma":0.001432832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02719079,"about_ca_topic_score_gemma":0.03138186,"domain_scores_codex":[0.9980518,0.0006411548,0.000186859,0.0005378072,0.0003982901,0.0001840032],"domain_scores_gemma":[0.9956425,0.001935611,0.0002170448,0.0006772989,0.001292695,0.0002348587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009119414,0.0005703114,0.02476206,0.004294705,0.0002609617,0.00383251,0.005764667,0.003197576,0.0313264,0.007928882,0.5713328,0.3458172],"study_design_scores_gemma":[0.0002473062,0.000226801,0.09143102,0.0005912043,0.0001278988,0.004972572,0.00335974,0.008393181,0.01255256,0.00252313,0.8753427,0.0002319087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.343623,0.01152777,0.04630568,0.001749315,0.001587827,0.001269531,0.5394951,0.01338538,0.04105642],"genre_scores_gemma":[0.2140039,0.001367819,0.04697345,0.0006445789,0.0003647603,0.001422697,0.7226179,0.001643907,0.01096094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02719079,"threshold_uncertainty_score":0.05406505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01537424476458782,"score_gpt":0.3110712238581493,"score_spread":0.2956969790935615,"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."}}