{"id":"W2806157614","doi":"10.1075/term.00012.amj","title":"Distributed specificity for automatic terminology extraction","year":2018,"lang":"en","type":"article","venue":"Terminology International Journal of Theoretical and Applied Issues in Specialized Communication","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Terminology; Artificial intelligence; Classifier (UML); Filter (signal processing); Natural language processing; Representation (politics); Domain (mathematical analysis); Pattern recognition (psychology); Computer vision; Linguistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000602428,0.0001400371,0.0003571798,0.0003288777,0.00008711033,0.00008012469,0.001684912,0.0001442904,0.00008016363],"category_scores_gemma":[0.0002544752,0.0001237947,0.00007863151,0.0001484331,0.0009587926,0.0003102068,0.0003661946,0.0002519523,0.000006065185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139656,"about_ca_system_score_gemma":0.00002708148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002667946,"about_ca_topic_score_gemma":0.000006330364,"domain_scores_codex":[0.9985374,0.0001421985,0.0007138874,0.0002081735,0.0002132786,0.0001850579],"domain_scores_gemma":[0.998149,0.0004647307,0.0005160295,0.0004471419,0.0003750375,0.00004800059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001365501,0.0001187344,0.0001375959,0.000002704486,0.00004329689,0.000005261978,0.000306769,0.000002308368,0.002484425,0.8884551,0.0002114836,0.1080958],"study_design_scores_gemma":[0.001113732,0.0002075396,0.002835205,0.00004614548,0.0000251635,0.0001857371,0.00008113847,0.006697954,0.02212559,0.9567363,0.009782816,0.0001627232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1656751,0.0002324488,0.8201202,0.01034882,0.0004292305,0.0002886013,0.00000716264,0.0001013705,0.002797034],"genre_scores_gemma":[0.8446758,0.0003840783,0.1544594,0.0001651309,0.0002649658,0.00001884223,0.00001157384,0.000006773431,0.00001343603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6790007,"threshold_uncertainty_score":0.50482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0178733567441031,"score_gpt":0.3525913017325484,"score_spread":0.3347179449884453,"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."}}