{"id":"W2141520705","doi":"10.1023/a:1026028229881","title":"Applying Machine Learning to Text Segmentation for Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Segmentation; Computer science; Text segmentation; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Word (group theory); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00109138,0.0001641134,0.0001531945,0.0003972802,0.0003189477,0.0005628691,0.0003651689,0.000102621,0.00002280603],"category_scores_gemma":[0.00113483,0.0001702474,0.00006952147,0.0007744515,0.00001037037,0.00702247,0.0000847463,0.0001909804,0.0003310138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001815788,"about_ca_system_score_gemma":0.0001139314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009044008,"about_ca_topic_score_gemma":7.178546e-7,"domain_scores_codex":[0.9982131,0.0000547674,0.0006964821,0.0001489014,0.0005632973,0.0003234305],"domain_scores_gemma":[0.9987821,0.0001184678,0.0003035023,0.0003027005,0.0003604657,0.0001327614],"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":[0.0004527553,0.000045205,0.0009856811,0.0003584147,0.00006416906,9.814225e-7,0.02396457,0.1227017,0.003111723,0.2245377,0.001238539,0.6225386],"study_design_scores_gemma":[0.001439928,0.0002376027,0.0001668019,0.00002677819,0.000009425885,0.00001809367,0.0005584903,0.586629,0.01444473,0.0007945496,0.3953047,0.0003699399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01314583,0.00001491661,0.9808013,0.0002860309,0.0005810044,0.001337618,0.00000948932,0.0002662791,0.003557491],"genre_scores_gemma":[0.7399691,0.000009288218,0.2564479,0.002910964,0.00008605512,0.0001279367,0.0002022341,0.00001322499,0.0002332498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7268233,"threshold_uncertainty_score":0.6942488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01664541220876287,"score_gpt":0.2556849407473694,"score_spread":0.2390395285386065,"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."}}