{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002611635,0.00008384592,0.0001062932,0.00006474793,0.0003456677,0.00005621154,0.0002529766,0.00007325257,7.257689e-7],"category_scores_gemma":[0.0001929896,0.00007112329,0.00009054879,0.0001788194,0.0000254442,0.00008350665,0.000008699598,0.00008121326,1.747645e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000572743,"about_ca_system_score_gemma":0.00004070944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008425446,"about_ca_topic_score_gemma":0.00001219162,"domain_scores_codex":[0.9992739,0.00002428516,0.0002343506,0.0001539149,0.0002009066,0.0001126633],"domain_scores_gemma":[0.9982671,0.0003059815,0.0001625264,0.0001116006,0.00113054,0.00002225712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001482603,0.0001956985,0.0004641765,0.0002356396,0.0002224423,1.199254e-7,0.002620172,0.3187037,0.0002610674,0.5493402,0.0004192555,0.1273893],"study_design_scores_gemma":[0.0003029204,0.00006176331,0.00004843361,0.000009314146,0.00003536963,9.226836e-7,0.000007593253,0.9146608,0.0002499123,0.08274306,0.001805808,0.00007415025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002366068,0.0003079817,0.9964927,0.001648284,0.0007440937,0.0003147929,0.000107442,0.0001002027,0.00004791327],"genre_scores_gemma":[0.5655377,0.000002020253,0.4339546,0.00006226112,0.0003811821,0.00001254278,0.0000132662,0.000005922686,0.00003053109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.595957,"threshold_uncertainty_score":0.2900323,"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."}}