{"id":"W3103720397","doi":"10.2196/23357","title":"Using Character-Level and Entity-Level Representations to Enhance Bidirectional Encoder Representation From Transformers-Based Clinical Semantic Textual Similarity Model: ClinicalSTS Modeling Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Harbin Institute of Technology","keywords":"Computer science; Natural language processing; Snippet; Artificial intelligence; Information retrieval; Encoder; Semantic similarity; Transformer; Sentence; Language model","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001277311,0.0002705176,0.000548025,0.0001409911,0.0002592344,0.0002429978,0.0007633077,0.0002697611,0.00003709635],"category_scores_gemma":[0.001067708,0.0002640803,0.0001574562,0.0005164047,0.00009569767,0.001268295,0.0004050121,0.0007984425,0.00002642273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005308897,"about_ca_system_score_gemma":0.0005009797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637431,"about_ca_topic_score_gemma":0.00008441267,"domain_scores_codex":[0.9951003,0.000237441,0.002111988,0.0006263214,0.001528656,0.0003953179],"domain_scores_gemma":[0.9974799,0.0006152453,0.0002894847,0.0005568961,0.0002404588,0.0008179772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004690101,0.003634261,0.06500994,0.0004499102,0.000587446,0.00008855346,0.09256066,0.5905256,0.0005602195,0.001447226,0.001082123,0.243585],"study_design_scores_gemma":[0.0009631715,0.0001259383,0.001939727,0.00007477126,0.00003976315,0.000003520209,0.001166234,0.9949316,0.00008464896,0.0003579869,0.00002783549,0.0002847624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4413509,0.000004388681,0.5561729,0.001589972,0.0001656017,0.0005176917,0.00002936278,0.00011105,0.00005811217],"genre_scores_gemma":[0.7735219,0.000014657,0.2216033,0.004511629,0.0002503454,0.00004699397,0.00002836336,0.00001406143,0.000008742724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.404406,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2662994500200416,"score_gpt":0.4595541498079628,"score_spread":0.1932546997879213,"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."}}