{"id":"W4385571527","doi":"10.18653/v1/2023.acl-short.112","title":"Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute for Catastrophic Loss Reduction","keywords":"Normalization (sociology); Machine translation; Computer science; Speech recognition; Artificial intelligence; Artificial neural network; Computational linguistics; Natural language processing; Deep neural networks; Sociology","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":[0.002603112,0.001072431,0.001010515,0.000589174,0.0006971442,0.001414229,0.001733467,0.001118718,0.005042239],"category_scores_gemma":[0.01302584,0.00044052,0.00045778,0.0008967069,0.0005388259,0.004617341,0.00116769,0.001139816,0.001501605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107679,"about_ca_system_score_gemma":0.001425857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008782985,"about_ca_topic_score_gemma":0.01407276,"domain_scores_codex":[0.9988802,0.0005268896,0.0000730799,0.0001861447,0.0001890522,0.0001445701],"domain_scores_gemma":[0.9957853,0.002777618,0.0001332337,0.0005528139,0.0006572382,0.00009376042],"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":[0.001859699,0.0007885847,0.005465495,0.0004923935,0.0002735217,0.0002672274,0.000258244,0.1988294,0.02784171,0.01555295,0.01021647,0.7381542],"study_design_scores_gemma":[0.00004939506,0.0002352204,0.0008423423,0.00002850371,0.00008949323,0.00006647123,0.0001281584,0.9726136,0.01511248,0.009540507,0.001280353,0.00001352187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4991732,0.009517545,0.4576469,0.001528907,0.0007290216,0.0001663271,0.0005328071,0.007666952,0.02303831],"genre_scores_gemma":[0.9099207,0.0007654795,0.08433744,0.0001848158,0.00008482508,0.00007913507,0.000759232,0.0005114271,0.003356953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008782985,"threshold_uncertainty_score":0.01746374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.157340779282443,"score_gpt":0.357068152226181,"score_spread":0.199727372943738,"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."}}