{"id":"W1965995772","doi":"10.1145/1458550.1458569","title":"Clustering the topics using TF-IDF for model fusion","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; tf–idf; Clef; Cluster analysis; Information retrieval; Task (project management); Variety (cybernetics); Question answering; Term (time); Data mining; Artificial intelligence; Machine learning","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":[0.006563021,0.002915428,0.002764647,0.007669288,0.001536039,0.002397629,0.002479235,0.002580724,0.0028344],"category_scores_gemma":[0.01817783,0.000963021,0.004478784,0.005600797,0.0007951364,0.003663378,0.001767211,0.003040297,0.003534688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001919369,"about_ca_system_score_gemma":0.001901556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01964384,"about_ca_topic_score_gemma":0.01252548,"domain_scores_codex":[0.9955987,0.001465461,0.0003901355,0.001207604,0.0008724417,0.00046572],"domain_scores_gemma":[0.9955276,0.001814504,0.000199291,0.001083248,0.001260984,0.000114493],"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":[0.0006500329,0.0004498957,0.004097215,0.0003396485,0.0005650046,0.0002847633,0.0010446,0.2237448,0.02619169,0.005394094,0.01101202,0.7262263],"study_design_scores_gemma":[0.00003246501,0.00008072844,0.001108387,0.0000274192,0.0001071666,0.0001210691,0.0001650506,0.9738175,0.01020867,0.01012565,0.00412134,0.00008457234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01141184,0.0002962595,0.9829444,0.0001151497,0.00007492879,0.0001706184,0.0005542035,0.004001114,0.0004314997],"genre_scores_gemma":[0.1616882,0.0003507927,0.8303968,0.00009196966,0.0001359662,0.0005740977,0.00457403,0.0007441395,0.001444004],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01964384,"threshold_uncertainty_score":0.03905898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05968255531486609,"score_gpt":0.3047592944829973,"score_spread":0.2450767391681312,"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."}}