{"id":"W2971077097","doi":"","title":"IBM Research System at TAC 2018: Deep Learning architectures for Drug-Drug Interaction extraction from Structured Product Labels.","year":2018,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"IBM; Computer science; Extraction (chemistry); Drug; Artificial intelligence; Product (mathematics); Chemistry; Pharmacology; Chromatography; Mathematics; Medicine; Nanotechnology; Materials science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001195276,0.001674663,0.0009842367,0.001581498,0.0005715493,0.001351658,0.002235638,0.001359587,0.0188198],"category_scores_gemma":[0.004469621,0.0008441933,0.001029937,0.002029401,0.0003002537,0.002265117,0.001467497,0.002222606,0.01191884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001346764,"about_ca_system_score_gemma":0.003121145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01776288,"about_ca_topic_score_gemma":0.02617709,"domain_scores_codex":[0.9995454,0.0001091455,0.00003214901,0.0001426413,0.0001197077,0.00005090456],"domain_scores_gemma":[0.9991898,0.0002928886,0.00005900348,0.0001788886,0.0002076833,0.00007178687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00142052,0.000599029,0.002758407,0.001063191,0.0005422271,0.0002202841,0.000173227,0.03629625,0.008429782,0.007394422,0.5642994,0.3768033],"study_design_scores_gemma":[0.0008779092,0.0005402424,0.001846027,0.0001883242,0.0002743495,0.0001677669,0.00009346796,0.7999468,0.01918204,0.03630763,0.1404881,0.00008731119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.07317344,0.0113656,0.3648437,0.004335729,0.00128351,0.0006768039,0.1403062,0.3806463,0.02336854],"genre_scores_gemma":[0.2193848,0.00334962,0.50359,0.001432908,0.0003260639,0.001496075,0.2308723,0.006776227,0.03277191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0188198,"threshold_uncertainty_score":0.06295854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01657871624875933,"score_gpt":0.3265698188233774,"score_spread":0.309991102574618,"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."}}