{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001208596,0.0000507835,0.00008087066,0.00001733017,0.00001525163,0.00001123655,0.0000699637,0.00006327165,4.936394e-7],"category_scores_gemma":[0.0003706001,0.00004538233,0.00002729728,0.00007952105,0.00002479025,0.000006874128,0.00001540059,0.00004154877,4.02948e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006136182,"about_ca_system_score_gemma":0.00001873059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000552331,"about_ca_topic_score_gemma":0.00004155564,"domain_scores_codex":[0.9995291,0.0000162271,0.00017334,0.000102761,0.0000607211,0.0001178953],"domain_scores_gemma":[0.9997512,0.00002730301,0.0001011797,0.00006151923,0.00002550694,0.00003329014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007988984,0.00001228302,0.008215033,0.0000328492,0.000004327791,1.111953e-7,0.0001606263,0.00004643761,0.01321261,8.254283e-7,0.00005236991,0.9781826],"study_design_scores_gemma":[0.003194354,0.0001251651,0.4340667,0.00002200721,0.00001563997,9.023778e-7,0.00254098,0.2104832,0.334048,0.00006330106,0.01508316,0.000356655],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.838533,0.001230287,0.1583972,0.001317794,0.00004616051,0.0003924115,0.00003484872,0.0000219172,0.00002641718],"genre_scores_gemma":[0.9951301,0.000003360428,0.004020844,0.0002783103,0.00008424214,0.0002565326,0.0002209199,0.000003786282,0.000001941597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.977826,"threshold_uncertainty_score":0.1850638,"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."}}