{"id":"W2514277269","doi":"","title":"Automatic supervised thesauri construction with roget's thesaurus","year":2012,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Thesaurus; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Measure (data warehouse); Word (group theory); Data mining; Linguistics","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":[0.004181372,0.001585961,0.001987442,0.006508684,0.002050998,0.003640889,0.00351114,0.001800725,0.008484702],"category_scores_gemma":[0.01900545,0.001491925,0.002711957,0.003752502,0.001767185,0.007222646,0.004652385,0.003324614,0.008122765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001861321,"about_ca_system_score_gemma":0.003229054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006781082,"about_ca_topic_score_gemma":0.01192073,"domain_scores_codex":[0.9943985,0.001538258,0.000625953,0.002193664,0.001066674,0.0001770394],"domain_scores_gemma":[0.9900383,0.003503975,0.0007910974,0.002389,0.003057274,0.0002204232],"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":[0.0002573954,0.0002886662,0.00319474,0.001244561,0.0002076185,0.0003613293,0.002220849,0.006487342,0.03814633,0.007932588,0.03338057,0.906278],"study_design_scores_gemma":[0.0004147218,0.0006884153,0.01521056,0.001037856,0.0005668334,0.002550421,0.004228546,0.500889,0.1200313,0.03908463,0.3147459,0.0005517416],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07353848,0.001504427,0.847865,0.0005238822,0.0006205511,0.002214116,0.003307479,0.05669121,0.01373488],"genre_scores_gemma":[0.09718618,0.0003685186,0.8813304,0.0002119745,0.00009492408,0.0007855199,0.01093305,0.002727374,0.006362171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008484702,"threshold_uncertainty_score":0.02838415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009785524150740084,"score_gpt":0.2342934763195165,"score_spread":0.2245079521687764,"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."}}