{"id":"W2769298630","doi":"10.1162/tacl_a_00011","title":"Modeling Past and Future for Neural Machine Translation","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Machine translation; Computer science; Decoding methods; Translation (biology); German; Artificial intelligence; Natural language processing; Mechanism (biology); Speech recognition; Machine learning; Algorithm; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0009135964,0.000661927,0.000573656,0.000706746,0.0005064672,0.00103737,0.001139442,0.000997578,0.003497413],"category_scores_gemma":[0.003884787,0.0004396403,0.0007793237,0.0009936851,0.0006861368,0.003852327,0.0009964558,0.001496551,0.001196276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007702792,"about_ca_system_score_gemma":0.0008198313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005292531,"about_ca_topic_score_gemma":0.008616557,"domain_scores_codex":[0.9996451,0.000112571,0.00003088503,0.0001269891,0.00005607917,0.0000283491],"domain_scores_gemma":[0.9990958,0.0004801086,0.00009373979,0.0001722119,0.0001296467,0.00002842471],"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":[0.0006674564,0.0001398943,0.004002566,0.0006286479,0.0002283574,0.0006800281,0.0009058699,0.3766472,0.02355266,0.1370159,0.008923014,0.4466084],"study_design_scores_gemma":[0.00001538698,0.00004534801,0.000562121,0.00003487427,0.0000686663,0.0001542176,0.00003344014,0.9291243,0.003420334,0.05931395,0.007203102,0.00002426573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04594436,0.004180486,0.9402043,0.001267262,0.0002635128,0.00003593666,0.0005661241,0.001776752,0.005761333],"genre_scores_gemma":[0.8307512,0.002509054,0.1570445,0.0003989066,0.0002552245,0.0001509475,0.00142869,0.0002499579,0.007211437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005292531,"threshold_uncertainty_score":0.01170003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01634169044876612,"score_gpt":0.2815328401993656,"score_spread":0.2651911497505995,"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."}}