{"id":"W2117770626","doi":"10.1186/2041-1480-2-s5-s11","title":"Assessment of NER solutions against the first and second CALBC Silver Standard Corpus","year":2011,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of New Brunswick","funders":"Concordia University; National Institute of Informatics; Universitat Jaume I; Magyar Tudományos Akadémia; Universidad Complutense de Madrid; Instituto de Salud Carlos III; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Universiteit Antwerpen; Institute of Information Science, Academia Sinica; Academia Sinica; Fondazione Bruno Kessler; Universitat Pompeu Fabra","keywords":"Annotation; Computer science; Natural language processing; Set (abstract data type); Information retrieval; Artificial intelligence; Named-entity recognition; Identification (biology); Task (project management)","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":[0.01622234,0.00314934,0.001776213,0.007254868,0.004131597,0.004464404,0.004332831,0.004647211,0.01221838],"category_scores_gemma":[0.04008444,0.0008336405,0.001502545,0.004667045,0.001904611,0.005292373,0.007011062,0.003500959,0.01237009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004647048,"about_ca_system_score_gemma":0.003354778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02884869,"about_ca_topic_score_gemma":0.0352674,"domain_scores_codex":[0.9848482,0.005217256,0.001459121,0.003269969,0.004435459,0.0007699557],"domain_scores_gemma":[0.9611128,0.01524314,0.001109315,0.005765111,0.01503791,0.001731705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.004235217,0.001981872,0.008345731,0.008969588,0.0007117029,0.001744829,0.005635523,0.01931226,0.05536585,0.008549973,0.5108233,0.3743241],"study_design_scores_gemma":[0.001932709,0.002246778,0.07492264,0.002255612,0.0006602399,0.004227811,0.01155129,0.1829839,0.124297,0.007877444,0.586273,0.0007716134],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4988708,0.009294843,0.1123341,0.009530649,0.005105942,0.006399713,0.1517556,0.08018822,0.1265202],"genre_scores_gemma":[0.2476182,0.00114691,0.1895649,0.001858368,0.0004248533,0.00409574,0.5196303,0.006749505,0.02891114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02884869,"threshold_uncertainty_score":0.08579296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245083958644906,"score_gpt":0.2709703653760666,"score_spread":0.246461969511576,"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."}}