{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009910172,0.002564004,0.002202743,0.003861217,0.001531266,0.002869094,0.001984956,0.002099946,0.02917485],"category_scores_gemma":[0.002229796,0.0008440466,0.001907286,0.003094906,0.000429223,0.003622387,0.002119092,0.002212506,0.02264765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005891934,"about_ca_system_score_gemma":0.00162079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005765282,"about_ca_topic_score_gemma":0.009168427,"domain_scores_codex":[0.9985791,0.000236373,0.0001254559,0.0005692358,0.0003462256,0.0001436745],"domain_scores_gemma":[0.9983391,0.0005368031,0.00006616305,0.0002633279,0.0006698029,0.0001247788],"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":[0.0006898867,0.0002300654,0.0004779895,0.0004720159,0.0001353586,0.0002605633,0.0002273155,0.003732407,0.1719147,0.003899141,0.03439333,0.7835672],"study_design_scores_gemma":[0.0002106429,0.0005844026,0.003658212,0.0001100942,0.0004627636,0.001126704,0.0007858861,0.7096117,0.1725136,0.01435231,0.0963772,0.0002065429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01399186,0.001221163,0.9419827,0.0006212687,0.0008817802,0.0004291929,0.002648412,0.03243456,0.005788951],"genre_scores_gemma":[0.08676156,0.0005905897,0.8768255,0.000481641,0.0006446001,0.0003287145,0.0106587,0.002973717,0.02073498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02917485,"threshold_uncertainty_score":0.09759957,"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."}}