{"id":"W2793238213","doi":"10.1075/term.00002.gha","title":"Automatic extraction of specialized verbal units","year":2017,"lang":"en","type":"article","venue":"Terminology International Journal of Theoretical and Applied Issues in Specialized Communication","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Computer science; Terminology; Natural language processing; Domain (mathematical analysis); Extractor; Artificial intelligence; Perspective (graphical); Quality (philosophy); Field (mathematics); Arabic; 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":[0.0006663873,0.0001153273,0.0003276791,0.0002386188,0.0001049541,0.0001613426,0.002928538,0.0001277237,0.00008507573],"category_scores_gemma":[0.0005035354,0.0000980047,0.00004469268,0.00007768307,0.0007961067,0.0004719918,0.0006507743,0.000331192,0.000002125347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005985367,"about_ca_system_score_gemma":0.00004921161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001502265,"about_ca_topic_score_gemma":0.000004754618,"domain_scores_codex":[0.9986878,0.0001370109,0.0006100387,0.000133991,0.0003107906,0.0001203531],"domain_scores_gemma":[0.9978539,0.0002340813,0.0009359351,0.0006094603,0.0003271498,0.00003945307],"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":[0.0001107372,0.00006928846,0.0001508503,0.000006467017,0.00002663237,0.0000148075,0.0006405942,6.257347e-7,0.003579611,0.8793614,0.00006491194,0.1159741],"study_design_scores_gemma":[0.001341215,0.00007647717,0.002722503,0.0001896742,0.00001743999,0.000192332,0.0000787658,0.001257312,0.03444022,0.9584101,0.001140022,0.0001338738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8924956,0.003893106,0.05586934,0.02358346,0.001574758,0.0004574838,0.000007620608,0.0001563433,0.02196228],"genre_scores_gemma":[0.8862234,0.000741833,0.1127992,0.00007177274,0.0001361152,0.00000392344,0.000002302237,0.000005454249,0.0000159038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1158402,"threshold_uncertainty_score":0.5442002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02029517479070884,"score_gpt":0.3476808911444303,"score_spread":0.3273857163537215,"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."}}