{"id":"W3034095843","doi":"10.14745/ccdr.46i06a06","title":"Application of natural language processing algorithms for extracting information from news articles in event-based surveillance.","year":2020,"lang":"en","type":"article","venue":"PubMed","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada; Response Biomedical (Canada); University of Toronto; Public Health Agency of Canada","funders":"","keywords":"Information extraction; Computer science; Event (particle physics); Focus (optics); Named-entity recognition; Information retrieval; Data science; Artificial intelligence; Natural language processing; Task (project management); Engineering","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":[0.006204484,0.001126507,0.0007695067,0.01251856,0.001092659,0.004012974,0.0009264519,0.0009874216,0.003821266],"category_scores_gemma":[0.02243689,0.0004451847,0.00131256,0.007577488,0.0007161378,0.003186082,0.001467173,0.001350321,0.003296149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095182,"about_ca_system_score_gemma":0.002587124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003483004,"about_ca_topic_score_gemma":0.005143807,"domain_scores_codex":[0.9955809,0.001566811,0.001005033,0.0006484226,0.001095526,0.000103324],"domain_scores_gemma":[0.9738287,0.0201453,0.001864624,0.0008838649,0.003039554,0.0002380038],"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":[0.0003615794,0.0004164791,0.01035359,0.008677178,0.0005930148,0.001951939,0.002211924,0.004290393,0.03996573,0.01558345,0.04689566,0.8686991],"study_design_scores_gemma":[0.0002627319,0.0004915322,0.03522321,0.003756184,0.001568444,0.004425931,0.005541547,0.175069,0.1295065,0.09062702,0.5531722,0.0003557384],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04056092,0.0138849,0.8537194,0.006479349,0.001108054,0.003927408,0.04552542,0.01381972,0.02097481],"genre_scores_gemma":[0.07877881,0.004693205,0.8791181,0.000624579,0.0003221266,0.0008734441,0.03206458,0.0003603782,0.003164774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01251856,"threshold_uncertainty_score":0.03281283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01894830637527734,"score_gpt":0.2632110314590011,"score_spread":0.2442627250837238,"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."}}