{"id":"W2970352405","doi":"10.18653/v1/w19-5326","title":"Multi-Source Transformer for Kazakh-Russian-English Neural Machine Translation","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Kazakh; Machine translation; Computer science; Transformer; Sentence; Natural language processing; Example-based machine translation; Artificial intelligence; Linguistics; Engineering; Voltage; Electrical engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002011928,0.0001592876,0.0001594363,0.00009860964,0.00007422066,0.000153997,0.0006650083,0.0000972926,0.00004276256],"category_scores_gemma":[0.00001986806,0.0001229224,0.0001089899,0.0002310094,0.00001706683,0.0009407212,0.00002133022,0.0001601523,0.00001474789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002086876,"about_ca_system_score_gemma":0.00002130987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003335222,"about_ca_topic_score_gemma":0.00002579322,"domain_scores_codex":[0.9989411,0.00002368535,0.000206084,0.0003714478,0.0001799023,0.0002777322],"domain_scores_gemma":[0.999404,0.00008024943,0.00004998264,0.0003333143,0.00007091085,0.00006153271],"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":[0.00004959972,0.0001107407,0.0005001183,0.0001563923,0.0000209457,0.000002071696,0.004303774,0.00007791237,0.02376719,0.01937075,0.0003834551,0.9512571],"study_design_scores_gemma":[0.00112149,0.0001450165,0.0001237755,0.00002304515,0.000008859537,0.000007539899,0.00002275062,0.9497185,0.0364554,0.001572158,0.01045633,0.0003451516],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001515156,0.001473059,0.992608,0.001104963,0.0002673858,0.0005997579,0.000004726867,0.001254356,0.001172633],"genre_scores_gemma":[0.4854458,0.000002342601,0.5131425,0.0003740969,0.00003418274,0.0000179036,0.00000777435,0.00001184083,0.0009635417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9509119,"threshold_uncertainty_score":0.501263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01586348264746504,"score_gpt":0.2679079498151393,"score_spread":0.2520444671676743,"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."}}