{"id":"W4377018759","doi":"10.32473/flairs.36.133326","title":"Improving Word Embedding Using Variational Dropout","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Dropout (neural networks); Word (group theory); Computer science; Word embedding; Artificial intelligence; Overfitting; Orthogonality; Natural language processing; Embedding; Curse of dimensionality; Inference; Machine learning; Mathematics; Artificial neural network","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":[0.00148661,0.00127406,0.001237275,0.0007053753,0.0004025884,0.000938547,0.001244108,0.001312122,0.002306706],"category_scores_gemma":[0.005767515,0.0005940022,0.0009441224,0.0009599549,0.000928903,0.003714071,0.001934314,0.002178186,0.001179271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008946741,"about_ca_system_score_gemma":0.001584064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006194534,"about_ca_topic_score_gemma":0.009136427,"domain_scores_codex":[0.9991894,0.0002777096,0.00005555251,0.0001981883,0.0001946113,0.00008455911],"domain_scores_gemma":[0.9984286,0.0008253852,0.0001231435,0.0002558579,0.0002995227,0.00006733058],"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":[0.0002578261,0.0002700956,0.00182205,0.0002584322,0.0001593593,0.0001697836,0.0003122741,0.5099939,0.0198684,0.02538582,0.01120568,0.4302964],"study_design_scores_gemma":[0.00000983785,0.00002441917,0.00008411009,0.000005178446,0.000007348428,0.00001468543,0.00001123915,0.991671,0.001954038,0.005548051,0.000664423,0.000005670918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02283635,0.000402941,0.974032,0.0002703129,0.00006891049,0.00003996668,0.0001219536,0.001351364,0.0008761932],"genre_scores_gemma":[0.4892154,0.000953303,0.496105,0.0006780776,0.000151392,0.0002735756,0.002209103,0.0006970065,0.009717136],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006194534,"threshold_uncertainty_score":0.01231694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1990856946383329,"score_gpt":0.3984730303623926,"score_spread":0.1993873357240597,"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."}}