{"id":"W4388477679","doi":"10.18280/ria.370513","title":"Enhancing Text Summarization with a T5 Model and Bayesian Optimization","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Bayesian optimization; Computer science; Bayesian probability; Artificial intelligence; Information retrieval; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.002849763,0.001212649,0.00131602,0.001796071,0.000664994,0.002022082,0.001405387,0.001741051,0.002371558],"category_scores_gemma":[0.008422908,0.0006152273,0.001524517,0.001464245,0.0004720915,0.002359403,0.001040914,0.001635389,0.001453157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001577024,"about_ca_system_score_gemma":0.001685178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01721243,"about_ca_topic_score_gemma":0.0179742,"domain_scores_codex":[0.9983884,0.0006653258,0.0001304657,0.0003303552,0.0003726752,0.0001128505],"domain_scores_gemma":[0.9967535,0.001790484,0.000235682,0.0001678951,0.0009690037,0.00008348702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003511598,0.0002903667,0.001510823,0.000345685,0.0002295244,0.0001177136,0.0004206643,0.5828714,0.009678149,0.008322912,0.008701068,0.3871605],"study_design_scores_gemma":[0.00001313658,0.00006100753,0.0002169468,0.00001229138,0.00003141135,0.00001772152,0.00003531289,0.9943154,0.001541241,0.002382915,0.001359934,0.00001265226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01704594,0.0006487045,0.9767653,0.0005070076,0.00007835695,0.0001769196,0.0002371848,0.002153106,0.002387511],"genre_scores_gemma":[0.2890221,0.0006903909,0.6994787,0.0004581113,0.0002115381,0.0005011732,0.001799621,0.0005908759,0.007247468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01721243,"threshold_uncertainty_score":0.03422445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03066239276200701,"score_gpt":0.2504901021751001,"score_spread":0.2198277094130931,"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."}}