{"id":"W3012108798","doi":"10.2196/17644","title":"Document-Level Biomedical Relation Extraction Leveraging Pretrained Self-Attention Structure and Entity Replacement: Algorithm and Pretreatment Method Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Relationship extraction; Computer science; Preprocessor; Relation (database); Semantics (computer science); Sentence; Context (archaeology); Noise (video); Artificial intelligence; Natural language processing; Heuristic; Data mining; Biomedical text mining; Information retrieval; Machine learning; Pattern recognition (psychology); Text mining; Image (mathematics)","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":[0.002920009,0.001590053,0.0009740721,0.002757132,0.000777499,0.001176654,0.001872529,0.001536417,0.003047212],"category_scores_gemma":[0.006870266,0.0003959734,0.001631707,0.002279949,0.000504104,0.002377306,0.001157367,0.001830342,0.002469863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117005,"about_ca_system_score_gemma":0.002105813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01023935,"about_ca_topic_score_gemma":0.01254792,"domain_scores_codex":[0.9983047,0.0003277538,0.0002125879,0.0006970645,0.000336368,0.0001215432],"domain_scores_gemma":[0.9960344,0.001518381,0.0002493882,0.0009622354,0.001132903,0.0001027781],"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":[0.0004801643,0.0005023329,0.009991102,0.0007440301,0.0003666955,0.0004746114,0.0002951796,0.02740621,0.02715041,0.001907369,0.01932616,0.9113558],"study_design_scores_gemma":[0.0001398551,0.0005152237,0.01692418,0.0001735129,0.0003462841,0.001072033,0.0003808237,0.8669761,0.08477473,0.003086162,0.02552487,0.00008615443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2491195,0.008919789,0.6992852,0.001038219,0.0006006365,0.001576303,0.006688138,0.02577526,0.00699692],"genre_scores_gemma":[0.3417667,0.00193615,0.6163245,0.0004417801,0.0001272731,0.0008759431,0.03105738,0.0004294689,0.00704074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01023935,"threshold_uncertainty_score":0.02035952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02101473833240067,"score_gpt":0.3257688454509995,"score_spread":0.3047541071185988,"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."}}