{"id":"W2252272516","doi":"10.18653/v1/w15-3014","title":"Montreal Neural Machine Translation Systems for WMT’15","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Canadian Institute for Advanced Research","keywords":"Machine translation; Leverage (statistics); Computer science; German; Natural language processing; Artificial intelligence; Variety (cybernetics); Machine translation system; Language model; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002323404,0.00008472653,0.00009957206,0.00005628733,0.00003839853,0.0001611566,0.0004335003,0.0000486397,0.000001038597],"category_scores_gemma":[0.00002731507,0.00006254316,0.00003259764,0.0001342426,0.000009832467,0.0004936272,0.00003712801,0.0000577575,0.00000394012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002481149,"about_ca_system_score_gemma":0.00002723753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005584879,"about_ca_topic_score_gemma":0.0000678468,"domain_scores_codex":[0.9993305,0.00002508392,0.0001343356,0.0001950521,0.0001645247,0.0001505063],"domain_scores_gemma":[0.9995116,0.00004317531,0.00004342049,0.0002212489,0.0001055914,0.00007494926],"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":[0.00005703034,0.00007266312,0.0002071596,0.000103031,0.00001805432,0.00001675056,0.001711472,0.0003810296,0.00103154,0.08705002,0.02255257,0.8867987],"study_design_scores_gemma":[0.0003089454,0.00008638867,0.00001289662,0.000007779051,0.000003451463,0.00001987083,0.00001138271,0.9866337,0.001062142,0.01003533,0.001707281,0.0001108853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002262904,0.01080503,0.9850587,0.0009481313,0.000259685,0.0002747895,0.000003166525,0.0008964789,0.001527697],"genre_scores_gemma":[0.6247633,0.000002096233,0.3745524,0.0001265598,0.0000638873,0.00002744789,0.000006585858,0.000006195861,0.000451616],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9862526,"threshold_uncertainty_score":0.2550436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03653425763530201,"score_gpt":0.2899250259595661,"score_spread":0.2533907683242641,"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."}}