{"id":"W2907526436","doi":"10.4000/books.aaccademia.4512","title":"Overview of the EVALITA 2018 Solving language games (NLP4FUN) Task","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Task (project management); Computer science; Set (abstract data type); Artificial intelligence; Range (aeronautics); Word (group theory); Natural language processing; World Wide Web; Multimedia; Human–computer interaction; Linguistics; Programming language; 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":[0.0003351872,0.0003944655,0.0004578886,0.0001664154,0.0002039934,0.00007770412,0.004721421,0.0007068821,0.00003842196],"category_scores_gemma":[0.00005508836,0.0003265479,0.0003034362,0.00003910238,0.000410155,0.0003680164,0.003416757,0.0009619857,0.00001010218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001907827,"about_ca_system_score_gemma":0.0001960966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002254403,"about_ca_topic_score_gemma":0.00001567063,"domain_scores_codex":[0.9980479,0.0001009804,0.0002945006,0.0006460251,0.0005783767,0.0003321656],"domain_scores_gemma":[0.9972869,0.0001453143,0.0006529238,0.001609976,0.0002114514,0.00009343932],"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":[0.00001971004,0.000009195713,0.000004162573,0.0003997478,0.0001510619,0.00006112632,0.003385106,3.135806e-7,0.001333719,0.9462689,0.03261916,0.01574776],"study_design_scores_gemma":[0.0003668977,0.00007174037,0.000009170558,0.002077914,0.0002449393,0.00003253094,0.00006216388,0.000200871,0.01986047,0.03044747,0.9457937,0.0008320913],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001307429,0.01547367,0.01059368,0.0002117747,0.0005842495,0.0008241651,0.000114978,0.0008987586,0.971168],"genre_scores_gemma":[0.002655029,0.0003125017,0.02486449,0.0003649946,0.0001939296,0.000001034476,0.0000061088,0.00005087184,0.9715511],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9158215,"threshold_uncertainty_score":0.9999186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03451380042961945,"score_gpt":0.2656893194680154,"score_spread":0.231175519038396,"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."}}