{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00237627,0.0009913505,0.001078429,0.005446508,0.000901314,0.002865026,0.001210839,0.001074287,0.003311928],"category_scores_gemma":[0.01181578,0.0004536994,0.00108803,0.004297035,0.001036539,0.004452992,0.003352716,0.001750808,0.003026148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000870625,"about_ca_system_score_gemma":0.001325697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000832958,"about_ca_topic_score_gemma":0.001165896,"domain_scores_codex":[0.9966226,0.001326659,0.0002872752,0.0008520795,0.0006975078,0.0002138606],"domain_scores_gemma":[0.9931479,0.002975618,0.000680967,0.001621379,0.001395846,0.0001782438],"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":[0.0002395529,0.0001074466,0.003834964,0.0004003486,0.0001291936,0.0002246335,0.0006224069,0.009597206,0.06565396,0.03488251,0.007645292,0.8766625],"study_design_scores_gemma":[0.00009367132,0.0002695493,0.007945208,0.0002072596,0.0002182325,0.001360352,0.0009424115,0.6510552,0.08586602,0.2060213,0.04589326,0.0001275092],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02484891,0.000444797,0.9689506,0.0002543571,0.00006028469,0.0001052607,0.0003088927,0.002403185,0.002623689],"genre_scores_gemma":[0.3636183,0.0003375965,0.6291032,0.0002082988,0.0001626884,0.0002486179,0.002292338,0.0005003171,0.003528541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005446508,"threshold_uncertainty_score":0.0125671,"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."}}