{"id":"W4386074631","doi":"10.11159/cist23.117","title":"Fine-Tuned PEGASUS: Exploring the Performance of the Transformer-Based Model on a Diverse Text Summarization Dataset","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Transformer; Computer science; Information retrieval; Natural language processing; Artificial intelligence; Engineering; Electrical engineering; Voltage","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":[0.002451591,0.0017269,0.0009481944,0.001923566,0.0006534885,0.001156608,0.001670721,0.001462354,0.001945434],"category_scores_gemma":[0.008518879,0.0002126678,0.001048945,0.001340207,0.0004958849,0.002544414,0.0009995245,0.001873429,0.001699042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001357961,"about_ca_system_score_gemma":0.0009386727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01075813,"about_ca_topic_score_gemma":0.01759175,"domain_scores_codex":[0.9990938,0.0003380651,0.00007405667,0.0003083165,0.000107375,0.0000783335],"domain_scores_gemma":[0.9974039,0.001427644,0.0001453282,0.0004100246,0.0004484943,0.0001645489],"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":[0.002438045,0.001355031,0.0104911,0.001514001,0.0007123859,0.0004312278,0.0005698777,0.282599,0.01595795,0.00296526,0.1093318,0.5716343],"study_design_scores_gemma":[0.0002109206,0.0008162597,0.003303314,0.00007726438,0.0001635631,0.0001349182,0.0003620504,0.9691431,0.01119688,0.004014628,0.01052349,0.00005353157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7562526,0.01504816,0.1477004,0.004858426,0.001500176,0.0007324526,0.0289983,0.03239813,0.01251138],"genre_scores_gemma":[0.7841818,0.001636412,0.1226405,0.001080594,0.0003885521,0.0004035526,0.08028517,0.000995398,0.008388101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01075813,"threshold_uncertainty_score":0.02139103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02388993777697735,"score_gpt":0.212355486743577,"score_spread":0.1884655489665997,"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."}}