{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001622594,0.0003615493,0.0006748181,0.0001941858,0.0001410602,0.0000430078,0.002934986,0.0007718123,0.00001707725],"category_scores_gemma":[0.00008850639,0.0003145969,0.000376435,0.00004800375,0.0003889807,0.0002549768,0.001134912,0.0003838753,0.00002091914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003214254,"about_ca_system_score_gemma":0.0006216939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001554072,"about_ca_topic_score_gemma":0.00007218066,"domain_scores_codex":[0.996554,0.0005095787,0.0005740979,0.0006110137,0.001458318,0.0002930171],"domain_scores_gemma":[0.9957937,0.0001813735,0.00125863,0.001792064,0.0008450595,0.0001291593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005097384,0.00002240737,0.00003263659,0.0006875808,0.0004277452,0.000007828321,0.001966254,0.00004703711,0.0003948323,0.962436,0.03127204,0.002654716],"study_design_scores_gemma":[0.002030588,0.0002235653,0.0002255902,0.002757815,0.001214815,0.00002482014,0.0001204965,0.002404069,0.002480481,0.01139439,0.9761687,0.0009546587],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0006567637,0.002657969,0.0009373564,0.0000369504,0.002960967,0.001864284,0.0003652998,0.00008991125,0.9904305],"genre_scores_gemma":[0.2012407,0.0004117128,0.0003501134,0.00009610716,0.001035166,0.000009820801,0.00007296313,0.00009262523,0.7966908],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9510416,"threshold_uncertainty_score":0.9999306,"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."}}