{"id":"W3029265130","doi":"","title":"Multilingual Dictionary Based Construction of Core Vocabulary.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Vocabulary; Natural language processing; Core (optical fiber); Artificial intelligence; Set (abstract data type); Bilingual dictionary; Field (mathematics); Resource (disambiguation); Machine translation; Linguistics; Programming language","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":[0.002659374,0.0006668834,0.0008988634,0.004443281,0.001119778,0.002789414,0.001350765,0.0006210512,0.01448565],"category_scores_gemma":[0.01356747,0.0004223374,0.0006385333,0.002629001,0.000666392,0.007674701,0.004650673,0.001208359,0.006870389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117116,"about_ca_system_score_gemma":0.003453089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007330266,"about_ca_topic_score_gemma":0.01202421,"domain_scores_codex":[0.995415,0.001957605,0.0006137853,0.0008134937,0.0009146866,0.0002854656],"domain_scores_gemma":[0.991949,0.002478808,0.0002621952,0.001129746,0.003834054,0.0003462859],"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":[0.001080108,0.0006002125,0.00880594,0.002004129,0.0002216377,0.0003888469,0.002459609,0.004986783,0.0610783,0.05857586,0.0412084,0.8185901],"study_design_scores_gemma":[0.0006009321,0.001316769,0.01681088,0.001060948,0.0008471427,0.002781912,0.01071279,0.3054191,0.2696757,0.1078484,0.2825933,0.00033204],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1510089,0.001600201,0.7510712,0.0005559606,0.0004962291,0.002355284,0.02160005,0.01650844,0.05480361],"genre_scores_gemma":[0.4719099,0.0006737193,0.4617526,0.0002099203,0.00007120408,0.001273349,0.04732143,0.002317864,0.01447015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01448565,"threshold_uncertainty_score":0.04845935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02869467135172208,"score_gpt":0.3027328626012327,"score_spread":0.2740381912495106,"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."}}