{"id":"W2888541716","doi":"10.18653/v1/d18-1398","title":"Meta-Learning for Low-Resource Neural Machine Translation","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tencent; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Computer science; Machine translation; Artificial intelligence; Romanian; Natural language processing; Transfer of learning; Representation (politics); BLEU; Translation (biology); Resource (disambiguation); Machine learning; Frame (networking); Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002090234,0.001293904,0.001368596,0.0009583265,0.0005764744,0.001309478,0.002406485,0.001789191,0.003481983],"category_scores_gemma":[0.005122149,0.000620242,0.001215951,0.001436203,0.0006719816,0.002834939,0.00160226,0.00217823,0.001776643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008652515,"about_ca_system_score_gemma":0.0009060726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001123857,"about_ca_topic_score_gemma":0.002029063,"domain_scores_codex":[0.9989098,0.0004950097,0.00008115457,0.000281973,0.0001496875,0.00008233185],"domain_scores_gemma":[0.9981107,0.001033869,0.0001344796,0.0004620809,0.000203631,0.00005535742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003584467,0.0002957315,0.001284326,0.0003946593,0.0004016053,0.0002396959,0.0001315654,0.4990323,0.01164756,0.01741122,0.00560353,0.4631994],"study_design_scores_gemma":[0.00002132222,0.0000602223,0.0001080497,0.0000147818,0.00002696073,0.00004356051,0.00001134248,0.9824935,0.002636717,0.0135002,0.00107348,0.000009827055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01747895,0.001255017,0.9759318,0.0003304542,0.000116521,0.00005353082,0.0001260305,0.002934858,0.001772853],"genre_scores_gemma":[0.5940461,0.0006266295,0.3987497,0.000599175,0.0002353413,0.0003759741,0.001027815,0.0004399758,0.003899393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003481983,"threshold_uncertainty_score":0.01164842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03958221554592636,"score_gpt":0.2951378261314581,"score_spread":0.2555556105855317,"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."}}