{"id":"W2407557870","doi":"10.63317/2ccdwd2a9gnc","title":"Detection of Domain Specific Terminology Using Corpora Comparison","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Terminology; Computer science; Term (time); Identification (biology); Focus (optics); Natural language processing; Task (project management); Domain (mathematical analysis); Artificial intelligence; Field (mathematics); Lexicography; Selection (genetic algorithm); Information retrieval; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001092719,0.00007745341,0.0001405808,0.000130362,0.00004852302,0.0000345754,0.0004305152,0.00007015499,0.000004340144],"category_scores_gemma":[0.000005580121,0.00006647323,0.00003077509,0.0002866602,0.00006158085,0.000249498,0.0001275229,0.0001049949,0.000005024796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007015026,"about_ca_system_score_gemma":0.00003082064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008674986,"about_ca_topic_score_gemma":0.00001391957,"domain_scores_codex":[0.9993212,0.00002200713,0.0002013106,0.0001966553,0.0001221391,0.0001366612],"domain_scores_gemma":[0.9994738,0.00001549665,0.0001400689,0.0002893687,0.00005566623,0.000025602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005994232,0.00005347855,0.0002238502,0.00001282097,0.000003975654,0.00001521028,0.0003176489,0.00004676037,0.7941254,0.1516412,0.00001359818,0.05354007],"study_design_scores_gemma":[0.0001605695,0.00007182755,0.0001313477,0.00001865267,0.000001364084,0.00006945197,0.00002099519,0.001321249,0.8559841,0.1418818,0.0002462419,0.00009241026],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1892978,0.0004726544,0.8095267,0.00006834833,0.0001123443,0.00005931083,1.651325e-7,0.0002772266,0.0001854557],"genre_scores_gemma":[0.5181133,0.000001262291,0.4818432,0.00002188472,0.00001194862,6.876833e-7,1.691926e-7,0.000002385582,0.000005136803],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3288155,"threshold_uncertainty_score":0.2710699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03402595291646539,"score_gpt":0.2916037686252727,"score_spread":0.2575778157088073,"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."}}