{"id":"W2140920152","doi":"10.1007/978-3-540-68825-9_27","title":"A Statistical Model for Topic Segmentation and Clustering","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Segmentation; Document clustering; Artificial intelligence; Statistical model; Brown clustering; Hierarchical clustering; Topic model; Bayesian probability; Natural language processing; Pattern recognition (psychology); Data mining; Fuzzy clustering; Canopy clustering algorithm","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":[0.0002858885,0.0002594038,0.000278965,0.0002774802,0.0001922376,0.0002356178,0.0008675925,0.0001482073,0.000002091798],"category_scores_gemma":[0.00004342447,0.0002523208,0.00003980301,0.00009290557,0.0002329464,0.0003517032,0.000641161,0.0002605908,0.000002060562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001487643,"about_ca_system_score_gemma":0.0002426279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008214754,"about_ca_topic_score_gemma":0.00004138003,"domain_scores_codex":[0.9978994,0.000009604705,0.0003186227,0.0009947267,0.0004132421,0.0003643704],"domain_scores_gemma":[0.9988772,0.0002869201,0.0001055211,0.0005331676,0.00009326841,0.0001038704],"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":[0.00000304587,0.000006051143,0.00001415532,0.00004873336,0.000003690488,0.00001478732,0.001295452,0.2423927,0.0000520306,0.01446724,0.00001125037,0.7416909],"study_design_scores_gemma":[0.0002026389,0.00005278683,0.00001775726,0.00007490642,0.000003205957,0.0000440079,6.873884e-8,0.9202782,0.00007677695,0.07892034,0.00008327522,0.0002460619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000870439,0.0001801759,0.998174,0.0003189957,0.0004980304,0.0003895801,0.000006342315,0.00007123806,0.0002746567],"genre_scores_gemma":[0.0498767,0.00004772476,0.9489816,0.0006795033,0.0001659495,0.00001430872,0.000003412668,0.00001496653,0.0002157683],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7414448,"threshold_uncertainty_score":0.9999929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0366026267238402,"score_gpt":0.2742441229591897,"score_spread":0.2376414962353495,"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."}}