{"id":"W2791176029","doi":"10.1016/j.neucom.2018.01.007","title":"Fine-grained attention mechanism for neural machine translation","year":2018,"lang":"en","type":"preprint","venue":"Neurocomputing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; National Research Foundation; Compute Canada; Samsung; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Machine translation; Computer science; Mechanism (biology); Translation (biology); Artificial intelligence; Context (archaeology); Word (group theory); Natural language processing; Exploit; Task (project management); Machine learning; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007030204,0.000437045,0.0006254075,0.0005362664,0.0005522846,0.001077714,0.00117713,0.001293653,0.009364428],"category_scores_gemma":[0.002682825,0.0002940463,0.0004507994,0.0007838256,0.000457835,0.002300085,0.001341197,0.001457323,0.001743438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006431993,"about_ca_system_score_gemma":0.0007961098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002176203,"about_ca_topic_score_gemma":0.003085145,"domain_scores_codex":[0.999678,0.00008316146,0.00002471862,0.0001034427,0.00004524304,0.00006543248],"domain_scores_gemma":[0.9992769,0.0002380028,0.00004514931,0.0002639395,0.0001330075,0.00004288141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006887857,0.0003588126,0.001116789,0.0003417426,0.0001429507,0.0003320113,0.0002490623,0.1241222,0.1030352,0.1886369,0.02524029,0.5557353],"study_design_scores_gemma":[0.00003334345,0.00008019446,0.0007228003,0.00001265715,0.00003202067,0.0001033575,0.000028043,0.8169814,0.01377552,0.1637294,0.004478055,0.00002321627],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06098735,0.001418616,0.9193196,0.001394938,0.0005382268,0.00007184536,0.0004217825,0.004273647,0.01157404],"genre_scores_gemma":[0.8747426,0.0004625344,0.112849,0.000398943,0.0002881731,0.00008289781,0.0004777059,0.0002254064,0.01047279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009364428,"threshold_uncertainty_score":0.03132713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03056099108739277,"score_gpt":0.29747321397155,"score_spread":0.2669122228841573,"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."}}