{"id":"W2100664567","doi":"10.3115/v1/p15-1001","title":"On Using Very Large Target Vocabulary for Neural Machine Translation","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":872,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Samsung; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Machine translation; Computer science; Vocabulary; Artificial intelligence; Natural language processing; Joint (building); Computational linguistics; Artificial neural network; Translation (biology); Volume (thermodynamics); Association (psychology); Speech recognition; Linguistics; Engineering; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003009144,0.00009826446,0.00009530745,0.00008359999,0.00006667075,0.00008895123,0.0003628797,0.00005449229,0.000004821757],"category_scores_gemma":[0.00004668352,0.00007810148,0.0000425358,0.0001627643,0.000008827958,0.0005393845,0.00005179142,0.00009063655,0.000003200706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003563575,"about_ca_system_score_gemma":0.00004070131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001967514,"about_ca_topic_score_gemma":0.000004375246,"domain_scores_codex":[0.9992588,0.00002765794,0.0001176312,0.0002204535,0.0001805922,0.0001949173],"domain_scores_gemma":[0.9995514,0.0000522962,0.00003978413,0.0002237916,0.00006887094,0.0000638119],"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":[0.0004520023,0.0006738876,0.0009366718,0.0002159063,0.00006380756,0.0001087859,0.004024729,0.003331001,0.01962354,0.5028878,0.02017535,0.4475065],"study_design_scores_gemma":[0.0003517732,0.0001062611,0.000004633208,0.000009875886,0.000002786524,0.000009203241,0.000003709229,0.9377556,0.01040753,0.05042594,0.0008013216,0.0001213845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003085866,0.001883202,0.9931664,0.0006326591,0.0002002813,0.0001831294,0.000005076132,0.0005502271,0.0002930991],"genre_scores_gemma":[0.4302039,2.939096e-7,0.5690862,0.0006095624,0.00003321874,0.000004214639,0.00000783437,0.000006369428,0.00004843116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9344246,"threshold_uncertainty_score":0.3184886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04490222195020935,"score_gpt":0.312351224200445,"score_spread":0.2674490022502356,"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."}}