{"id":"W3161027543","doi":"10.2196/29667","title":"A Word Pair Dataset for Semantic Similarity and Relatedness in Korean Medical Vocabulary: Reference Development and Validation","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Korea Health Industry Development Institute","keywords":"Natural language processing; Computer science; Similarity (geometry); Vocabulary; Word (group theory); Word embedding; Task (project management); Artificial intelligence; Semantic similarity; Set (abstract data type); Health informatics; Information retrieval; Unified Medical Language System; Embedding; Linguistics; Medicine; Pathology","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":[0.007252385,0.001723819,0.000996526,0.009116691,0.001698983,0.001486215,0.002588488,0.002023978,0.004649746],"category_scores_gemma":[0.02437861,0.0004513414,0.001765982,0.004675097,0.001307229,0.0034175,0.004624798,0.001861321,0.006120738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205947,"about_ca_system_score_gemma":0.002416572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005567947,"about_ca_topic_score_gemma":0.008453181,"domain_scores_codex":[0.9924465,0.002204836,0.002304182,0.001527993,0.001241466,0.0002750563],"domain_scores_gemma":[0.9831212,0.005960446,0.001569864,0.003944595,0.004556676,0.0008473413],"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":[0.00328022,0.004837065,0.1590519,0.01351965,0.001397242,0.004900286,0.00827767,0.008662685,0.03563637,0.007216568,0.2838804,0.4693399],"study_design_scores_gemma":[0.003252512,0.003767702,0.4419279,0.00220717,0.001366517,0.009025086,0.01267187,0.08588516,0.04280968,0.007293947,0.3889674,0.0008252051],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6162636,0.004060528,0.04659209,0.0008009635,0.0007137313,0.008496229,0.3081327,0.005854665,0.009085399],"genre_scores_gemma":[0.1913272,0.0005727219,0.07232732,0.0002725319,0.00009414983,0.007704388,0.7251674,0.0003126113,0.002221702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009116691,"threshold_uncertainty_score":0.03835469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03191483108306381,"score_gpt":0.317044660720137,"score_spread":0.2851298296370732,"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."}}