{"id":"W2147840212","doi":"10.1007/978-3-540-39935-3_22","title":"Enhanced phrase-based document clustering using Self-Organizing Map (SOM) architectures","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Self-organizing map; Phrase; Cluster analysis; Computer science; Artificial intelligence; Natural language processing; Document clustering","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":[0.0006141935,0.0005531576,0.001019443,0.001467628,0.0005074452,0.001182891,0.001270707,0.0007475854,0.002524198],"category_scores_gemma":[0.001994992,0.0002833939,0.000750732,0.003156238,0.0002920954,0.001531335,0.0009192962,0.000720871,0.001771618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004070309,"about_ca_system_score_gemma":0.0006058277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003434198,"about_ca_topic_score_gemma":0.00525732,"domain_scores_codex":[0.9995174,0.00008123786,0.00004188428,0.0000938238,0.0002296419,0.00003600009],"domain_scores_gemma":[0.9989868,0.0003084529,0.00004579289,0.0001273808,0.0004946854,0.00003683248],"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":[0.0003208359,0.0001772557,0.0008116447,0.0002651308,0.0001308741,0.00009579097,0.0001884299,0.02659554,0.03882381,0.003342028,0.007186589,0.922062],"study_design_scores_gemma":[0.00005143921,0.0001505417,0.002508356,0.00003152823,0.0001293801,0.0003181604,0.0001246778,0.9354284,0.04314125,0.01004811,0.008001409,0.00006666213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03024241,0.0009903006,0.962436,0.000116615,0.0001437621,0.00008776284,0.0004471751,0.003015759,0.002520164],"genre_scores_gemma":[0.1388672,0.0006098635,0.8530227,0.00008724805,0.0001180105,0.0001150371,0.001383789,0.0002217754,0.005574328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003434198,"threshold_uncertainty_score":0.008444309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03531482692826102,"score_gpt":0.2978583838462532,"score_spread":0.2625435569179921,"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."}}