{"id":"W3206379208","doi":"10.1007/978-3-030-89022-3_26","title":"Empirically Evaluating the Semantic Qualities of Language Vocabularies","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina; University of Toronto; York University","funders":"","keywords":"Computer science; Operationalization; Vocabulary; Set (abstract data type); Documentation; Domain (mathematical analysis); Meaning (existential); Natural language processing; Design language; Artificial intelligence; Human–computer interaction; Software engineering; Programming language; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02069671,0.0006158718,0.0005787241,0.003858445,0.001063233,0.005292526,0.00134293,0.001680386,0.003335781],"category_scores_gemma":[0.2183102,0.0004261079,0.0006243182,0.003707263,0.002177906,0.01106852,0.002498522,0.00159044,0.0003278639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001754939,"about_ca_system_score_gemma":0.001552086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006074898,"about_ca_topic_score_gemma":0.008114083,"domain_scores_codex":[0.9866283,0.008175922,0.001201009,0.00101445,0.00257835,0.0004019322],"domain_scores_gemma":[0.6789151,0.2999968,0.007233542,0.005745301,0.006846582,0.001262667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00625501,0.00187646,0.3952824,0.002110814,0.00124845,0.0006158293,0.007896435,0.1002977,0.01652254,0.1500249,0.007342585,0.3105269],"study_design_scores_gemma":[0.0009224591,0.002237444,0.1267514,0.001020407,0.001331215,0.001034531,0.02089068,0.6085138,0.01730368,0.2062455,0.01350575,0.0002432319],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9677975,0.00124095,0.01701715,0.0009136006,0.00004040755,0.0001245998,0.0008757356,0.0001495615,0.01184062],"genre_scores_gemma":[0.9857439,0.000214765,0.01225587,0.00006210194,0.00001602549,0.0000463921,0.001296542,0.00004447114,0.0003200289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02069671,"threshold_uncertainty_score":0.1094559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04808444048484034,"score_gpt":0.3274641631340492,"score_spread":0.2793797226492089,"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."}}