{"id":"W2792207007","doi":"10.5539/ijel.v8n3p357","title":"A Corpus-Based Approach to Lexicography: A New English-Russian Phraseological Dictionary","year":2018,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Bilingual dictionary; Lexicography; Natural language processing; Linguistics; Artificial intelligence; Corpus linguistics; Perspective (graphical); Phrase; Process (computing); Lexicographical order; Component (thermodynamics); Term (time); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0002674954,0.0002036107,0.0002585501,0.000502069,0.0002026994,0.0002323023,0.000546187,0.00006816214,0.0006107042],"category_scores_gemma":[0.01615586,0.000160482,0.0002991527,0.0001159672,0.0004177463,0.00008699887,0.00007551104,0.0003235147,0.00001186843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004805679,"about_ca_system_score_gemma":0.0001339793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005782653,"about_ca_topic_score_gemma":0.00006615862,"domain_scores_codex":[0.9983448,0.00004971012,0.0005418799,0.0001992345,0.0006286064,0.0002357025],"domain_scores_gemma":[0.9852727,0.0001694211,0.0003114438,0.0001357715,0.0138888,0.0002218702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001160176,0.001219991,0.005606462,0.00002389069,0.001133145,0.0001285107,0.1044268,0.0002778245,0.000004130041,0.7019637,0.1815821,0.002473344],"study_design_scores_gemma":[0.0008558008,0.0005521551,0.0006759735,0.00007315866,0.00006879757,0.000002111654,0.002616346,0.00005419987,0.0000598882,0.002835215,0.9920004,0.0002059569],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01338489,0.000751223,0.004123847,0.0001944882,0.05699504,0.0001973592,0.0001516754,0.0001703698,0.9240311],"genre_scores_gemma":[0.8836195,0.00002046506,0.004043709,0.001419953,0.1104525,0.000003817086,0.00001971939,0.00002009215,0.0004002197],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9236309,"threshold_uncertainty_score":0.9921315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02925431521164802,"score_gpt":0.2673371528925573,"score_spread":0.2380828376809093,"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."}}