{"id":"W3157414336","doi":"10.25073/2588-1086/vnucsce.237","title":"Single Concatenated Input is Better than Indenpendent Multiple-input for CNNs to Predict Chemical-induced Disease Relation from Literature","year":2020,"lang":"en","type":"article","venue":"VNU Journal of Science Computer Science and Communication Engineering","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Foundation for Science and Technology Development","keywords":"Concatenation (mathematics); Computer science; Biomedical text mining; Convolutional neural network; Benchmark (surveying); Relation (database); Named-entity recognition; Artificial intelligence; Natural language processing; Data mining; Text mining; Mathematics; Task (project management); Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005185233,0.00009880227,0.0001174676,0.0001224066,0.000161805,0.0001662914,0.0009131869,0.00005803305,6.437002e-7],"category_scores_gemma":[0.0006242953,0.00008189855,0.0000387888,0.0005707611,0.0003390537,0.00006636347,0.0003645032,0.0001450352,4.968384e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003183306,"about_ca_system_score_gemma":0.0001413576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001822754,"about_ca_topic_score_gemma":2.018002e-7,"domain_scores_codex":[0.9989401,0.00001420347,0.0002400757,0.0002577947,0.0003585977,0.0001891992],"domain_scores_gemma":[0.9988122,0.00004815475,0.0001192527,0.0002628004,0.0004065711,0.0003510212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003333576,0.00002227231,0.001266838,0.000008155669,0.000008518776,0.000001047854,0.001178986,0.0004843889,0.9692858,0.000009450673,0.0001147316,0.02758645],"study_design_scores_gemma":[0.001006045,0.0007187075,0.04145143,0.0003266603,0.00002413303,0.00001946596,0.0001273687,0.3787646,0.5734277,0.00009228307,0.003709828,0.0003317715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.844416,0.0004750988,0.1507232,0.004138832,0.00013281,0.000091227,0.000008264758,0.00001211043,0.000002499586],"genre_scores_gemma":[0.9522985,0.00004120322,0.04642971,0.001078918,0.0001346825,0.00000373979,0.000007082266,0.000005008856,0.000001186293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3958581,"threshold_uncertainty_score":0.3339726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02200202434629777,"score_gpt":0.2493643346008226,"score_spread":0.2273623102545248,"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."}}