{"id":"W193970460","doi":"10.1007/978-3-642-34752-8_11","title":"Improving Supervised Keyphrase Indexer Classification of Keyphrases with Text Denoising","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Information retrieval; Pattern recognition (psychology)","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":[0.001346636,0.001535211,0.002255551,0.003147478,0.0005256835,0.001644961,0.001324723,0.001623323,0.003686516],"category_scores_gemma":[0.004011854,0.0003603284,0.00121373,0.002215907,0.0004595143,0.002095062,0.001236414,0.001677404,0.008272681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004171133,"about_ca_system_score_gemma":0.0008054437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001974928,"about_ca_topic_score_gemma":0.003399901,"domain_scores_codex":[0.9986922,0.0001823233,0.00009688669,0.0003584992,0.0005017993,0.0001682844],"domain_scores_gemma":[0.9972573,0.0008886777,0.0002154353,0.0005674291,0.0009291457,0.0001420403],"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":[0.0009350859,0.0002486074,0.001350594,0.0002040604,0.00008249433,0.0001137253,0.00005475037,0.005381874,0.127905,0.0009667955,0.01007037,0.8526866],"study_design_scores_gemma":[0.00006939111,0.0003335889,0.003917682,0.00003240599,0.0001464881,0.0004420126,0.0001157063,0.8803622,0.102298,0.002876482,0.009358563,0.0000475781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09837098,0.003390591,0.8795751,0.0004020696,0.0005790713,0.0002031565,0.0013969,0.01255528,0.00352687],"genre_scores_gemma":[0.366847,0.001901825,0.5967061,0.0004384556,0.0008967751,0.0002160682,0.007325082,0.001121836,0.02454686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003686516,"threshold_uncertainty_score":0.01233262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01874575708455064,"score_gpt":0.253253565720815,"score_spread":0.2345078086362644,"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."}}