{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001685924,0.00008289995,0.0001040164,0.00007505402,0.00003078644,0.00001372027,0.0001014832,0.0001682004,0.00001721264],"category_scores_gemma":[0.0003719651,0.00006081001,0.00002501435,0.0001090975,0.00017595,0.000003647049,0.00006033746,0.00009629008,0.000002204439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003129698,"about_ca_system_score_gemma":0.0000517091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928103,"about_ca_topic_score_gemma":0.00001655748,"domain_scores_codex":[0.9994208,0.00001528426,0.0001847136,0.0001276324,0.0001300762,0.0001214528],"domain_scores_gemma":[0.9996489,0.00002080564,0.00003729897,0.0001279316,0.00006647779,0.00009860576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002267013,0.00003590287,0.0006032878,0.00003824527,0.00001307969,5.157415e-7,0.0002308111,0.0003056515,0.9529884,0.00005472469,0.0007045713,0.04479805],"study_design_scores_gemma":[0.001778973,0.001244177,0.002703399,0.000104385,0.00001100248,0.000008385417,0.001979865,0.7729259,0.1937057,0.00005698556,0.02513848,0.0003427491],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.87262,0.000007756603,0.1260185,0.0006576132,0.0001065506,0.00007837813,0.00001538256,0.00001824232,0.0004775715],"genre_scores_gemma":[0.9713856,0.000005116363,0.02768868,0.0007812841,0.00002655386,0.000002600471,0.00006237592,0.000003195483,0.00004462428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7726202,"threshold_uncertainty_score":0.247976,"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."}}