{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002340805,0.001185265,0.001679018,0.004115161,0.001110679,0.002500342,0.001268672,0.001517651,0.003127824],"category_scores_gemma":[0.00960903,0.0007180565,0.001551814,0.003868007,0.0008875153,0.003265153,0.001038711,0.00174213,0.00299296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234185,"about_ca_system_score_gemma":0.001421111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00624612,"about_ca_topic_score_gemma":0.006248933,"domain_scores_codex":[0.9980595,0.0009328028,0.0001661074,0.0003937302,0.0003157029,0.0001322089],"domain_scores_gemma":[0.994518,0.003997478,0.0002636971,0.000485777,0.0006177155,0.000117413],"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":[0.0003393371,0.0003601187,0.001841152,0.000602051,0.0002307993,0.0001377912,0.0004224027,0.05574257,0.03849183,0.008367009,0.01118995,0.8822751],"study_design_scores_gemma":[0.00004460394,0.0001103723,0.001212593,0.00003842956,0.0001122746,0.0001072889,0.0001463887,0.9312439,0.02028291,0.04036074,0.006301579,0.00003882279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0164607,0.001856822,0.9744391,0.0004295451,0.0001664203,0.0001914365,0.000233325,0.004581825,0.001640817],"genre_scores_gemma":[0.1985327,0.001685588,0.7919687,0.0002758656,0.0005119633,0.0003276343,0.001710998,0.0008884883,0.004098064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00624612,"threshold_uncertainty_score":0.01241952,"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."}}