{"id":"W3035908455","doi":"10.1007/978-3-030-51310-8_18","title":"Literary Natural Language Generation with Psychological Traits","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Parsing; Creativity; Computer science; Artificial intelligence; Natural language processing; Text generation; Natural language generation; Natural (archaeology); Personality; Literary language; Linguistics; Natural language; Psychology; History; Philosophy; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003219388,0.000487694,0.0004227873,0.0003707928,0.0001840093,0.0007220854,0.002922811,0.0002564034,0.00003102131],"category_scores_gemma":[0.00007491116,0.0003696516,0.00009928765,0.000625395,0.0006607918,0.0007517642,0.0006382312,0.001016391,0.0000998699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344423,"about_ca_system_score_gemma":0.0001941652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005237266,"about_ca_topic_score_gemma":0.00004517857,"domain_scores_codex":[0.9963792,0.00004289279,0.0004432407,0.001713959,0.0009163335,0.0005043819],"domain_scores_gemma":[0.9984146,0.0002171509,0.0002034111,0.0008202258,0.0001643081,0.0001802651],"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":[0.000009652253,0.00002316101,0.00001096223,0.00001039941,0.000007067821,0.0004142159,0.002764773,0.003607032,0.001285411,0.01756399,0.00004522749,0.9742581],"study_design_scores_gemma":[0.0001536502,0.0006513291,0.0001211416,0.0002438622,0.000008365547,0.0003634083,7.063285e-7,0.9232827,0.008690287,0.06479244,0.0006626406,0.001029469],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007091543,0.0009939914,0.9917356,0.001675255,0.001221355,0.0003363125,0.000003615134,0.0002566997,0.003068025],"genre_scores_gemma":[0.6523415,0.00001215313,0.3428075,0.003695117,0.0009049402,0.000007305231,0.000007449597,0.00002445085,0.000199525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9732286,"threshold_uncertainty_score":0.9998755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03215910308621596,"score_gpt":0.2888146522133143,"score_spread":0.2566555491270983,"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."}}