{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008414372,0.0006104237,0.0007396308,0.001368079,0.0002186843,0.0002899551,0.003046426,0.0003309736,0.00002133124],"category_scores_gemma":[0.0001073889,0.0005120454,0.000150209,0.001131269,0.0009390831,0.001616367,0.001014856,0.0007184339,0.00001254941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000372693,"about_ca_system_score_gemma":0.0005065033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005368895,"about_ca_topic_score_gemma":0.0001106715,"domain_scores_codex":[0.9958001,0.00004646818,0.0007352934,0.001458881,0.001245949,0.0007132819],"domain_scores_gemma":[0.9960128,0.000456986,0.0007818416,0.002056492,0.0004950934,0.0001967686],"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":[0.00001325689,0.00006046214,0.0007392203,0.00007374192,0.00002093465,0.00002313389,0.0005585979,0.004146297,0.00942197,0.01413265,0.000003148178,0.9708066],"study_design_scores_gemma":[0.001059413,0.0006297079,0.002091411,0.001722939,0.0001331025,0.0001563633,0.000002508749,0.7863518,0.1199764,0.0846947,0.0005012907,0.002680398],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001369395,0.0007522478,0.9961672,0.0001488129,0.0002022463,0.000412218,0.000003467739,0.0002659926,0.0006784177],"genre_scores_gemma":[0.5133864,0.0000301922,0.4861855,0.0001628903,0.0001380978,0.00000974813,0.000004915952,0.00003546647,0.00004673127],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9681262,"threshold_uncertainty_score":0.9997331,"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."}}