{"id":"W4402703397","doi":"10.1007/978-3-031-67317-7_9","title":"Machine Learning Based Extractive Text Summarization Using Document Aware and Document Unaware Features","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in systems, decision and control","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Natural language processing; Artificial intelligence; World Wide Web","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":[0.0007517402,0.0005430409,0.001076295,0.0006277086,0.0002821555,0.0004043606,0.0003157432,0.0002441941,0.000007436513],"category_scores_gemma":[0.0001351032,0.0004318592,0.0001238687,0.000153151,0.0001352701,0.0003446962,0.0005184625,0.0005756678,0.00000555283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004268534,"about_ca_system_score_gemma":0.00005204116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007368706,"about_ca_topic_score_gemma":0.00009915673,"domain_scores_codex":[0.9971598,0.0001219386,0.0007778732,0.001009487,0.0006548326,0.0002760772],"domain_scores_gemma":[0.9977903,0.0009192095,0.0004567963,0.0004586746,0.0002874037,0.00008763428],"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":[0.0004556387,0.00006372336,0.0009993966,0.001821777,0.002874819,0.001305668,0.003560704,0.01659489,0.0001125441,0.4297252,0.001799652,0.540686],"study_design_scores_gemma":[0.005721862,0.0008237204,0.0002169268,0.01964942,0.001163567,0.0002299193,0.00223111,0.4360575,0.00004504035,0.2989252,0.2316831,0.003252578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0000363357,0.1825579,0.8091364,0.0002591627,0.0009074786,0.001385523,0.00002310209,0.0003155115,0.005378642],"genre_scores_gemma":[0.9016917,0.01658864,0.01137961,0.0003073262,0.0002908061,0.000227781,0.00003569393,0.0001387871,0.0693397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9016553,"threshold_uncertainty_score":0.9998133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02520959795395034,"score_gpt":0.3316281685645455,"score_spread":0.3064185706105952,"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."}}