{"id":"W2794604371","doi":"10.1101/262790","title":"Transfer learning for biomedical named entity recognition with neural networks","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"National Institutes of Health; Nvidia","keywords":"Computer science; Transfer of learning; Named-entity recognition; Artificial intelligence; Deep learning; Annotation; Conditional random field; Task (project management); Artificial neural network; Field (mathematics); Natural language processing; Machine learning; Word (group theory); Noise (video); State (computer science); Deep neural networks; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004151504,0.001724692,0.00109006,0.002535355,0.0005923407,0.00114057,0.002620769,0.00206699,0.004082663],"category_scores_gemma":[0.008821734,0.0004640681,0.001026056,0.002472862,0.0009047786,0.003596935,0.002190924,0.002273164,0.002383418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00184659,"about_ca_system_score_gemma":0.001136626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00646481,"about_ca_topic_score_gemma":0.005024794,"domain_scores_codex":[0.9981833,0.0005820905,0.0001351884,0.0005775666,0.0003645299,0.0001573608],"domain_scores_gemma":[0.9952873,0.002509786,0.0003670811,0.0008332705,0.0008993072,0.0001032281],"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":[0.0003354634,0.0003359738,0.002544477,0.0003008037,0.0002179547,0.0002578521,0.0001043875,0.3784073,0.00620711,0.003594802,0.01161706,0.5960768],"study_design_scores_gemma":[0.00001252619,0.00004753317,0.0005388749,0.00002029748,0.00002017668,0.00002955105,0.0000334289,0.9840447,0.006726301,0.006894995,0.001616587,0.0000151557],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1619516,0.005210984,0.7914001,0.002035634,0.0007126911,0.0004405806,0.002679891,0.02824197,0.007326534],"genre_scores_gemma":[0.7886421,0.001062219,0.1933101,0.0006208855,0.0002979271,0.0004753816,0.008467924,0.0003102023,0.006813291],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00646481,"threshold_uncertainty_score":0.02195555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685541585094678,"score_gpt":0.2328407093391094,"score_spread":0.2159852934881626,"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."}}