{"id":"W2130063192","doi":"10.1145/1854776.1854820","title":"Unsupervised mapping of sentences to biomedical concepts based on integrated information retrieval model and clustering","year":2010,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Unified Medical Language System; Information retrieval; Cluster analysis; Annotation; Natural language processing; Task (project management); Scope (computer science); Artificial intelligence; Matching (statistics); Thesaurus; Precision and recall","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":[0.002231307,0.001324789,0.001417631,0.008683351,0.0008674105,0.001672462,0.002016322,0.001458486,0.001712564],"category_scores_gemma":[0.00837125,0.000430102,0.001921549,0.006016873,0.0007811866,0.003324241,0.001328671,0.001054612,0.001858551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408888,"about_ca_system_score_gemma":0.00224939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008543693,"about_ca_topic_score_gemma":0.007573678,"domain_scores_codex":[0.9971915,0.0007467532,0.0003229298,0.0008938877,0.0006817263,0.0001631458],"domain_scores_gemma":[0.9961268,0.001627058,0.0003376666,0.0005633048,0.001254577,0.00009048341],"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":[0.0006414334,0.0007341972,0.008132645,0.00118847,0.0004057755,0.0007839937,0.002374104,0.04658347,0.07888933,0.01719294,0.01961483,0.8234587],"study_design_scores_gemma":[0.0001062727,0.0003012855,0.008626115,0.00009493197,0.000284739,0.0009049008,0.0008281093,0.9106459,0.03696572,0.02827478,0.01281371,0.000153545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05762292,0.0009543164,0.9316953,0.0005246334,0.000104133,0.0007266363,0.00123686,0.004903629,0.002231525],"genre_scores_gemma":[0.2003228,0.0005445441,0.7897419,0.0002714911,0.0001012012,0.00072069,0.005017822,0.0003319173,0.002947523],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008683351,"threshold_uncertainty_score":0.01698792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01595974769222175,"score_gpt":0.2750378388191956,"score_spread":0.2590780911269739,"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."}}