{"id":"W2977455214","doi":"10.4000/books.aaccademia.4437","title":"Evalita 2018: Overview on the 6th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Natural (archaeology); Computer science; Natural language processing; Linguistics; Psychology; Speech recognition; History; Archaeology; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.0009407715,0.0002184028,0.0002531777,0.0000840416,0.0002136873,0.0001173356,0.0009312379,0.0003199595,0.00001265819],"category_scores_gemma":[0.0001219496,0.0001793218,0.0001058605,0.00001804871,0.0002038767,0.0004074186,0.000273476,0.0003271697,0.000002651768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001546662,"about_ca_system_score_gemma":0.0001632373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004674114,"about_ca_topic_score_gemma":0.00001688301,"domain_scores_codex":[0.9985678,0.0001098466,0.0002114219,0.0004886197,0.0004496021,0.0001727147],"domain_scores_gemma":[0.9981583,0.0004448576,0.0003649011,0.0006702606,0.0003082071,0.00005341235],"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":[0.00008164559,0.00001446884,0.000002756751,0.0003836488,0.00008097608,0.000002560577,0.005443378,0.000004057017,0.0002179045,0.5041206,0.002948777,0.4866992],"study_design_scores_gemma":[0.002232176,0.0006111331,0.0004688133,0.002480658,0.0009968693,0.00003193946,0.001511964,0.03612586,0.00885375,0.04259567,0.90232,0.001771117],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01641485,0.006748274,0.02048475,0.001449001,0.0007384604,0.008667788,0.0004283745,0.0003943589,0.9446741],"genre_scores_gemma":[0.4341006,0.0002116879,0.004792223,0.0006327506,0.0004083499,0.00001892236,0.0001342195,0.00006834519,0.5596329],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8993713,"threshold_uncertainty_score":0.731253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1062257194990996,"score_gpt":0.3005297298892182,"score_spread":0.1943040103901186,"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."}}