{"id":"W2777929561","doi":"10.48550/arxiv.1712.08207","title":"Variational Attention for Sequence-to-Sequence Models","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sequence (biology); Encoder; Computer science; Artificial neural network; Set (abstract data type); Gaussian; Algorithm; Latent variable; Random sequence; Artificial intelligence; Mechanism (biology); Mathematics; Physics","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":[0.003371793,0.001116615,0.001298521,0.001101112,0.0006328974,0.001267321,0.002597612,0.002223382,0.003829599],"category_scores_gemma":[0.01182874,0.00093316,0.001309969,0.001218214,0.001285739,0.002654854,0.002018272,0.002758711,0.0006886747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002042472,"about_ca_system_score_gemma":0.001459411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01012877,"about_ca_topic_score_gemma":0.01034935,"domain_scores_codex":[0.9983022,0.0008169527,0.00007768128,0.0004486215,0.0002283419,0.000126137],"domain_scores_gemma":[0.995016,0.004152459,0.0001802347,0.0002877491,0.0002534958,0.0001100653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001220427,0.00007077465,0.0008625399,0.0001626838,0.000126556,0.0001507659,0.0002754378,0.7379979,0.002796914,0.1936118,0.003722842,0.06009982],"study_design_scores_gemma":[0.000005608513,0.000008512628,0.00007204954,0.000004486777,0.000006655233,0.00001531897,0.000005450337,0.9545179,0.0001988305,0.04460127,0.0005578534,0.000005932732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006415564,0.0005812427,0.9912845,0.0003558518,0.0000428379,0.00003153912,0.0001274649,0.0002423484,0.0009185756],"genre_scores_gemma":[0.670016,0.001683865,0.3127006,0.0006636935,0.0003754185,0.0004856836,0.001322136,0.0004633625,0.0122893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01012877,"threshold_uncertainty_score":0.02013963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2599454264256302,"score_gpt":0.242695120612733,"score_spread":0.01725030581289716,"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."}}