{"id":"W2949176808","doi":"10.1093/bioinformatics/bty449","title":"Transfer learning for biomedical named entity recognition with neural networks","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health; Nvidia","keywords":"Computer science; Named-entity recognition; Transfer of learning; Artificial intelligence; Annotation; Deep learning; Conditional random field; Task (project management); Artificial neural network; Field (mathematics); Machine learning; Natural language processing; Word (group theory); Noise (video); State (computer science); Domain (mathematical analysis); Mathematics","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":[0.0001888,0.0001183135,0.0001194463,0.0000344309,0.0001421619,0.0000290077,0.0001147732,0.0002133854,0.00002067956],"category_scores_gemma":[0.000129622,0.00008703393,0.00005733778,0.00009030176,0.0003583857,0.000007409122,0.00002878983,0.0001044764,0.00001019999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006782525,"about_ca_system_score_gemma":0.00003298074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003000968,"about_ca_topic_score_gemma":0.00001207586,"domain_scores_codex":[0.9992521,0.00002047677,0.0002118491,0.0001290638,0.0001188375,0.0002676552],"domain_scores_gemma":[0.9996086,0.0000245179,0.00004362079,0.0001238768,0.0001035403,0.00009587263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000854324,0.0001355821,0.001137183,0.0001755411,0.0001787619,0.000002345744,0.0005947266,0.0001185694,0.005960059,0.00004195139,0.01033137,0.9804696],"study_design_scores_gemma":[0.004446417,0.01036505,0.0008362375,0.0001146986,0.0001377851,0.0001055128,0.001398442,0.4602784,0.0206426,0.00008546953,0.5007209,0.0008684802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4322612,0.00007835414,0.5663976,0.0002045117,0.0002876129,0.0002208108,0.0000175299,0.00006139461,0.0004709908],"genre_scores_gemma":[0.9712829,0.00003940825,0.02678259,0.000514942,0.0006010988,0.00003147093,0.0005723304,0.00001555719,0.000159701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9796011,"threshold_uncertainty_score":0.3549141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01989986393970058,"score_gpt":0.2556185910061561,"score_spread":0.2357187270664556,"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."}}