{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002424116,0.0002244348,0.0002070097,0.0005697908,0.0007875945,0.00165083,0.003777751,0.00008696755,0.00000236644],"category_scores_gemma":[0.0004002349,0.0002064016,0.00008682539,0.004133649,0.0003020104,0.002111492,0.00110849,0.0001792337,0.00009667011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001158165,"about_ca_system_score_gemma":0.0004190471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009797446,"about_ca_topic_score_gemma":0.000007426252,"domain_scores_codex":[0.9967517,0.00002975012,0.0003921105,0.0011632,0.0007736411,0.000889591],"domain_scores_gemma":[0.9979267,0.000203001,0.000219378,0.0008311094,0.0006383785,0.0001814431],"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":[0.00002084074,0.000327023,0.009838697,0.0005390857,0.00002798272,0.0000700567,0.01027735,0.0001426088,0.1051632,0.3888525,0.02100476,0.4637358],"study_design_scores_gemma":[0.0006059214,0.0001852711,0.0117116,0.00008044594,0.000005286995,0.00005520408,0.000006460736,0.6021117,0.07649897,0.3044789,0.003580303,0.0006799469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02542374,0.0002979257,0.9691344,0.0006412276,0.001536849,0.0005882686,0.00001307716,0.002318542,0.00004588965],"genre_scores_gemma":[0.418148,0.000007899516,0.5808688,0.0003362963,0.0002571457,0.0001946843,0.00001010627,0.00001481726,0.0001622516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6019691,"threshold_uncertainty_score":0.9993855,"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."}}