{"id":"W2907819441","doi":"10.4000/books.aaccademia.4487","title":"Overview of the EVALITA 2018 Evaluation of Italian DIALogue systems (IDIAL) Task","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Task (project management); Perspective (graphical); Computer science; Human–computer interaction; Protocol (science); Artificial intelligence; Engineering; Systems engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.01946217,0.002039845,0.001562744,0.004655347,0.001653886,0.005835234,0.00308638,0.001800301,0.01607976],"category_scores_gemma":[0.01129802,0.0007524345,0.000931925,0.002888959,0.0009815941,0.002613335,0.00467562,0.002280375,0.01633011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003135887,"about_ca_system_score_gemma":0.00472749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005287613,"about_ca_topic_score_gemma":0.006633785,"domain_scores_codex":[0.9856188,0.006306539,0.0009564087,0.001308337,0.005158796,0.0006510132],"domain_scores_gemma":[0.9914751,0.002402559,0.0004037929,0.00112356,0.003852493,0.0007425],"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":[0.0008084796,0.001382436,0.001788698,0.005510079,0.000139397,0.0002128441,0.003448944,0.004087997,0.02189844,0.009332987,0.278707,0.6726827],"study_design_scores_gemma":[0.0002652667,0.001244836,0.008418882,0.001493822,0.00009002585,0.0003828721,0.0008870937,0.005544338,0.01700781,0.005678997,0.9588214,0.000164661],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.05786728,0.07003199,0.3113802,0.007825891,0.003021513,0.02376107,0.03999664,0.02458595,0.4615295],"genre_scores_gemma":[0.1665892,0.01942245,0.4610366,0.003431731,0.002187339,0.03327737,0.1360893,0.009415209,0.1685508],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.01946217,"threshold_uncertainty_score":0.102927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1077046938195312,"score_gpt":0.2708445794023639,"score_spread":0.1631398855828328,"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."}}