{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003209216,0.00008095968,0.0001076653,0.00006053844,0.0000631257,0.00003888663,0.0001779331,0.00005721932,0.00002909522],"category_scores_gemma":[0.0001419278,0.00007070444,0.0000294744,0.000223837,0.00005443563,0.0001698917,0.00006831094,0.00008845132,0.000001464314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001447902,"about_ca_system_score_gemma":0.00003738974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003461879,"about_ca_topic_score_gemma":0.000002109799,"domain_scores_codex":[0.9991015,0.00006617505,0.0001644725,0.0002230227,0.0003566006,0.00008821044],"domain_scores_gemma":[0.9995005,0.00005559146,0.0001232702,0.0001474862,0.0001196489,0.00005354384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004722909,0.00002751455,0.001932321,0.0001279233,0.0000159695,0.00001079689,0.01441785,0.0002407699,0.03708238,0.001577666,0.00009510119,0.9444245],"study_design_scores_gemma":[0.0005740243,0.0001627974,0.001146585,0.0000636292,0.00003147709,0.00001770938,0.0007635974,0.9300492,0.06511497,0.001631118,0.0002903273,0.0001545559],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8814127,0.00689925,0.1101129,0.0008683192,0.0000569303,0.0002161714,0.00000485066,0.0002619232,0.0001669232],"genre_scores_gemma":[0.8237203,0.000007697978,0.175916,0.0002643305,0.00006426348,0.000006243601,0.00001256872,0.000004742057,0.000003925054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9442699,"threshold_uncertainty_score":0.2883243,"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."}}