{"id":"W1966427115","doi":"10.1145/2232817.2232866","title":"Investigating keyphrase indexing with text denoising","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Search engine indexing; Computer science; Benchmark (surveying); Noise reduction; Artificial intelligence; Natural language processing; Noise (video); Energy (signal processing); Pattern recognition (psychology); Information retrieval; Image (mathematics); 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":[0.006485353,0.001678414,0.00189548,0.004473083,0.0009816521,0.002901827,0.002078602,0.001743198,0.00272408],"category_scores_gemma":[0.02914221,0.0004216479,0.00108862,0.004104866,0.001601915,0.007039226,0.0020706,0.001860736,0.003539369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022721,"about_ca_system_score_gemma":0.001195478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004195049,"about_ca_topic_score_gemma":0.004908188,"domain_scores_codex":[0.9958051,0.001088241,0.0004186572,0.0009478551,0.001459059,0.0002809599],"domain_scores_gemma":[0.9839464,0.009824095,0.000983668,0.002852474,0.002011904,0.0003814384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001963399,0.0006784911,0.006596769,0.001894594,0.0003462993,0.0003299237,0.001061374,0.02744484,0.1375902,0.003888853,0.01195332,0.806252],"study_design_scores_gemma":[0.0002667449,0.00228456,0.01345755,0.0001338706,0.0003584833,0.001273913,0.001264505,0.5637904,0.3711853,0.007937811,0.0377946,0.0002522784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5229497,0.01354365,0.4099396,0.00128992,0.000998739,0.0008614235,0.003660324,0.03153271,0.015224],"genre_scores_gemma":[0.5098613,0.002435711,0.4574386,0.0005377815,0.0006503186,0.0004476278,0.01552735,0.00129644,0.0118048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006485353,"threshold_uncertainty_score":0.03429824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01774092605419382,"score_gpt":0.2694506596691447,"score_spread":0.2517097336149509,"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."}}