{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002608344,0.00009654289,0.0001251176,0.00006599577,0.0001434245,0.0001260526,0.0004792586,0.00004356469,0.00004384087],"category_scores_gemma":[0.00003773248,0.00006807264,0.00009069624,0.0001899614,0.0000303344,0.0003745814,0.0000593789,0.000102363,0.000007661855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008745717,"about_ca_system_score_gemma":0.000009146138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001434867,"about_ca_topic_score_gemma":0.00001065211,"domain_scores_codex":[0.999295,0.00003732439,0.0001272862,0.0002392583,0.0001307893,0.0001703265],"domain_scores_gemma":[0.999546,0.00009254467,0.00005170565,0.0001996106,0.00007393125,0.00003624024],"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":[0.00002479167,0.00003045075,0.00003408533,0.00003990811,0.0001283596,0.000002736883,0.001165759,0.00004271081,0.01062027,0.02191309,0.001316547,0.9646813],"study_design_scores_gemma":[0.0001719902,0.0001661412,0.000007223409,0.000005083944,0.00006502985,0.000009069543,0.000004605351,0.9066583,0.07205158,0.006985784,0.01371199,0.0001631986],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003464139,0.001958863,0.9939473,0.00152307,0.00004973244,0.0001487503,5.217443e-7,0.0009695186,0.001055838],"genre_scores_gemma":[0.4727885,4.639161e-7,0.5260844,0.0004638508,0.00006163114,0.00001386993,0.000002753548,0.000006261732,0.0005781632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9645181,"threshold_uncertainty_score":0.2775922,"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."}}