{"id":"W2089697781","doi":"10.3414/me10-01-0020","title":"Effectiveness of Lexico-syntactic Pattern Matching for Ontology Enrichment with Clinical Documents","year":2010,"lang":"en","type":"article","venue":"Methods of Information in Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"National Human Genome Research Institute; National Cancer Institute; University of Pittsburgh","keywords":"Computer science; Matching (statistics); Sentence; Natural language processing; Set (abstract data type); Ontology; Information retrieval; Domain (mathematical analysis); Artificial intelligence; Mathematics; Statistics","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":[0.003999094,0.00009044247,0.0003360451,0.00009104663,0.00001654205,0.000002188853,0.0001433721,0.0001772462,0.00001435166],"category_scores_gemma":[0.001477251,0.00006060213,0.0000411948,0.00007198108,0.0002612985,0.000009972769,0.00003843701,0.0001471453,4.244725e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005832993,"about_ca_system_score_gemma":0.00004435913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008365799,"about_ca_topic_score_gemma":0.00001936651,"domain_scores_codex":[0.9988015,0.0002632132,0.0005871924,0.0001074517,0.0001169462,0.0001236989],"domain_scores_gemma":[0.9986988,0.0006382847,0.0003123615,0.0001940126,0.0001152697,0.00004121988],"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":[0.001445831,0.0001521966,0.05987772,0.001239254,0.0001545971,6.963535e-7,0.0007854753,0.00003560168,0.1838206,0.0004001721,0.0002316533,0.7518563],"study_design_scores_gemma":[0.01924695,0.01118871,0.432656,0.001205991,0.0001852428,0.00005641235,0.002579443,0.0007333527,0.4901035,0.004453397,0.03702808,0.0005628935],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4997364,0.00004383326,0.499369,0.0001271596,0.0002648762,0.000192674,0.000002940778,0.000003827233,0.0002592913],"genre_scores_gemma":[0.8130344,0.0000303207,0.1866582,0.0001207415,0.00004754443,0.00004401772,0.00005204971,0.000004098904,0.000008592197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7512934,"threshold_uncertainty_score":0.2471283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02669870627091075,"score_gpt":0.4329955275027238,"score_spread":0.406296821231813,"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."}}