{"id":"W2970009562","doi":"10.18653/v1/w19-5431","title":"Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Machine translation; Nepali; Computer science; Czech; Natural language processing; Artificial intelligence; Example-based machine translation; Transformer; Transfer-based machine translation; Translation (biology); Hindi; Portuguese; Task (project management); Linguistics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001399708,0.001031745,0.0007390305,0.0008031815,0.0006128232,0.001792779,0.001226198,0.0008816583,0.006325079],"category_scores_gemma":[0.006281544,0.0003528104,0.001008149,0.00150429,0.0006331996,0.002924561,0.001937376,0.0016095,0.002840514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007698727,"about_ca_system_score_gemma":0.001479703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007299488,"about_ca_topic_score_gemma":0.01322955,"domain_scores_codex":[0.9988183,0.000427153,0.00008425824,0.0003308497,0.0002078589,0.0001314475],"domain_scores_gemma":[0.9981528,0.0006981003,0.0001296731,0.0005707583,0.0004001801,0.00004842916],"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":[0.000580288,0.0004912817,0.005598766,0.0008096785,0.0005325297,0.001243049,0.001060257,0.1412386,0.0378831,0.02391001,0.01667793,0.7699745],"study_design_scores_gemma":[0.00009202764,0.0003099956,0.002676827,0.0000872263,0.0001994593,0.0007382594,0.0003529276,0.8913879,0.04762138,0.03603078,0.02042254,0.00008067022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2715715,0.001620392,0.6843951,0.001193922,0.0005335426,0.0002197658,0.003052609,0.007477324,0.02993575],"genre_scores_gemma":[0.7987539,0.0004183474,0.1834965,0.000385601,0.0001364395,0.0001041741,0.00557069,0.0007013291,0.01043297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007299488,"threshold_uncertainty_score":0.02115947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005545113999298296,"score_gpt":0.2324726324775448,"score_spread":0.2269275184782465,"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."}}