{"id":"W3198035914","doi":"10.1007/978-3-030-86337-1_16","title":"A More Effective Sentence-Wise Text Segmentation Approach Using BERT","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Segmentation; Encoder; Artificial intelligence; Sentence; Transformer; Natural language processing; Text segmentation; Feature (linguistics); Heuristic; Feature engineering; Language model; Deep learning; Natural language","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":[0.0008445561,0.0005704154,0.0005746083,0.0006611748,0.0003039268,0.0006742346,0.002246485,0.0003147796,0.00001071252],"category_scores_gemma":[0.00009435467,0.0005462355,0.0001703684,0.0007671978,0.0004440487,0.0008074908,0.00163609,0.0008140887,0.00001083551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006635214,"about_ca_system_score_gemma":0.0006008184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006987053,"about_ca_topic_score_gemma":0.0000175415,"domain_scores_codex":[0.9954032,0.00006606943,0.0005109187,0.002142993,0.001210464,0.0006663568],"domain_scores_gemma":[0.9973789,0.0003682815,0.0002966704,0.00145594,0.0003241242,0.0001760701],"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":[0.000003848046,0.0000441975,0.0001043655,0.00008912833,0.00002387895,0.0001344885,0.002660353,0.223611,0.001325931,0.005974418,0.000004188729,0.7660242],"study_design_scores_gemma":[0.0002389931,0.00004616355,0.00005860449,0.0003902406,0.00001382199,0.0001813414,0.000001844971,0.9843735,0.002396238,0.01167413,0.00005561336,0.0005695001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007082036,0.0005385808,0.9950225,0.000281848,0.001337578,0.0007307814,0.000003014254,0.0001381353,0.001239382],"genre_scores_gemma":[0.063673,0.00001907556,0.9343735,0.001152762,0.0004806636,0.00002229314,0.000009752216,0.00003759987,0.0002313217],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7654546,"threshold_uncertainty_score":0.9996989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02597573277663658,"score_gpt":0.2658582777646642,"score_spread":0.2398825449880276,"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."}}